From 70a7faf8c96ca1623f68819fe693b90cac87327e Mon Sep 17 00:00:00 2001 From: Can Date: Fri, 16 Jan 2026 14:35:15 +0300 Subject: [PATCH] Fix metadata --- Llama3_1_(8B)_Alpaca-ASFT.ipynb | 6078 +++++++------------------------ 1 file changed, 1327 insertions(+), 4751 deletions(-) diff --git a/Llama3_1_(8B)_Alpaca-ASFT.ipynb b/Llama3_1_(8B)_Alpaca-ASFT.ipynb index 98031d91a5..e5314aacce 100644 --- a/Llama3_1_(8B)_Alpaca-ASFT.ipynb +++ b/Llama3_1_(8B)_Alpaca-ASFT.ipynb @@ -1,4806 +1,1382 @@ { - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "x_wPZgziQKXy" - }, - "source": [ - "To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n", - "
\n", - "\n", - "\n", - " Join Discord if you need help + ⭐ Star us on Github ⭐\n", - "
\n", - "\n", - "This notebook is an **ASFT / ASFT+ demo** (Anchored Supervised Fine-Tuning).\n", - "\n", - "Credits:\n", - "- ASFT paper & reference implementation: https://github.com/zhuchichi56/ASFT\n", - "- ASFT+ (this optimized Unsloth integration + extra speed/perf optimizations): Can (cansolakoglu130@gmail.com) X/Twitter @HCSolakoglu\n", - "\n", - "To install Unsloth your local device, follow [our guide](https://docs.unsloth.ai/get-started/install-and-update). This notebook is licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).\n", - "\n", - "You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save)\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "t-ahwuyvQKXz" - }, - "source": [ - "### News" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "TiJUkQ5MQKX0" - }, - "source": [ - "\n", - "Introducing FP8 precision training for faster RL inference. [Read Blog](https://docs.unsloth.ai/new/fp8-reinforcement-learning).\n", - "\n", - "Unsloth's [Docker image](https://hub.docker.com/r/unsloth/unsloth) is here! Start training with no setup & environment issues. [Read our Guide](https://docs.unsloth.ai/new/how-to-train-llms-with-unsloth-and-docker).\n", - "\n", - "[gpt-oss RL](https://docs.unsloth.ai/new/gpt-oss-reinforcement-learning) is now supported with the fastest inference & lowest VRAM. Try our [new notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt-oss-(20B)-GRPO.ipynb) which creates kernels!\n", - "\n", - "Introducing [Vision](https://docs.unsloth.ai/new/vision-reinforcement-learning-vlm-rl) and [Standby](https://docs.unsloth.ai/basics/memory-efficient-rl) for RL! Train Qwen, Gemma etc. VLMs with GSPO - even faster with less VRAM.\n", - "\n", - "Visit our docs for all our [model uploads](https://docs.unsloth.ai/get-started/all-our-models) and [notebooks](https://docs.unsloth.ai/get-started/unsloth-notebooks).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "vXSL0oj6QKX0" - }, - "source": [ - "### Installation" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "krAQhz2yQKX0" - }, - "outputs": [], - "source": [ - "%%capture\n", - "import os, re\n", - "\n", - "IN_COLAB = \"COLAB_\" in \"\".join(os.environ.keys())\n", - "\n", - "if not IN_COLAB:\n", - " # ASFT demo: if you're running this notebook from the Unsloth repo/branch,\n", - " # an editable install is the most reliable way to ensure ASFTTrainer is present.\n", - " if os.path.exists(\"pyproject.toml\"):\n", - " %pip install -e \".[cu126-torch290]\"\n", - " else:\n", - " %pip install -U unsloth\n", - "else:\n", - " # Do this only in Colab notebooks! Otherwise use pip install unsloth / pip install -e .\n", - " import torch; v = re.match(r\"[0-9]{1,}\\.[0-9]{1,}\", str(torch.__version__)).group(0)\n", - " xformers = \"xformers==\" + (\"0.0.33.post1\" if v==\"2.9\" else \"0.0.32.post2\" if v==\"2.8\" else \"0.0.29.post3\")\n", - " %pip install --no-deps bitsandbytes accelerate {xformers} peft trl triton cut_cross_entropy unsloth_zoo\n", - " %pip install sentencepiece protobuf \"datasets==4.3.0\" \"huggingface_hub>=0.34.0\" hf_transfer\n", - " %pip install --no-deps unsloth\n", - "\n", - "%pip install transformers==4.56.2\n", - "%pip install --no-deps trl==0.22.2" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "S68-v0avQKX1" - }, - "source": [ - "### Unsloth" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 300, - "referenced_widgets": [ - "6e3c281f112b4a86af7a3ef95933d221", - "92395f250a154006923aaf9ea0a9c30b", - "f84bfc5390054ec687c157c4d68199a6", - "4228734651ca45e19fc7bda79817f9b3", - "4613edbbec6846edb5b1677c25d542b6", - "d032fe2ba5d647d99026fdade758c0cd", - "e9971d220fe24552a1e9aa299765cfb9", - "2be29a4553ad4dfea8a9bc620c81a3ae", - "94cbb87829d1486899e2ff6325c2ecdf", - "f878c2e00bc240c7b0333cce950080e1", - "6b908368de51428585552dfef6a83088", - "ac5eacaaee8346c080e54ea7a52648a4", - "7981edf408d54d41bbeac42da7492c6b", - "2b848e5a85bc42bc87945fd9ed5db038", - "e88c33f37d6849e0b1a6b41254104cb9", - "33843107b93647b28985bfc37ea781ca", - "76e5410e286a4a5abd6c213a38aa38bb", - "ae7e90a811f94e75997d6a9ed1be8596", - "bb9f3379310d4b04be694996f3137b28", - "75082ba15db445df907f5612976590ae", - "89934c4f26834f15b9889ec36fee3b65", - "e887160635cb4803b9f33845df615ec6", - "1c7bc5fdb7dd4c39af8d4c2c504ec3ed", - "843a27e619534ea8914f9d36386c364b", - "8f5adc70fbf248f2811527f620553be5", - "4ffb4b2f015046fb94c1115ed0397a20", - "5a232ed040f94633a2a374031284c1f6", - "2006be31c09349738e221295bb84939f", - "07055fc12b0841aaa5317f8252b5d347", - "1eb90e686e214122ae763b1b79ae321d", - "7a935956348e47c68fbdf05ddf4752f3", - "8653acb618ad4e76bbf1daa00ea71238", - "e3c3bd9c4c124b0a8c88c83c1fc747d3", - "1bd75ddaf57c4438a4e2c3070b9cef65", - "a3a3ef6d6337403cabea8b23f7c3021b", - "c2ea0a3f01f34ffa8c94ab9b5098e9da", - "68ea1d7cb8274a639b3fb5326f4218c3", - "39fef7b257614a0595f39355fa226b69", - "d125995cc0934239a01ba01b78529f21", - "634ae4c6cfe04673b1cdc9c9cac4cbf9", - "d7f92e8332374313bee87ccd427446a4", - "36799fbcd90d43128620ff98225a825d", - "5310346dd579424fa676b8e8e64790e7", - "0c1835f404db4846bb13b5da8d8f4447", - "29c5b713f07043dda51820523e5c8ff3", - "d7375f0f048841b29a20601c122666e8", - "f433ced9bfcd4a57ba691d3c1caeed08", - "da8ffc70820a48f5a12c6d4b5967015b", - "1a6db9aea6a64ae3aaef51d6265b35b2", - "331f516c7a76456d801bc2a2feb228aa", - "9be9074028da42d39d044a78393a861f", - "51cd9026b1664819a67712996ca97bd5", - "ea55293415ca48a4be97c2e1e4769122", - "8ea52b105a7e44978caca33c0e7e815b", - "3662f1445ef34a50b462e601ed31bb69" - ] - }, - "id": "QmUBVEnvCDJv", - "outputId": "0a47b925-663d-4543-9c61-994a6302f3c5" - }, - "outputs": [ + "cells": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", - "==((====))== Unsloth 2024.8: Fast Llama patching. Transformers = 4.44.2.\n", - " \\\\ /| GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.\n", - "O^O/ \\_/ \\ Pytorch: 2.4.0+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.\n", - "\\ / Bfloat16 = FALSE. FA [Xformers = 0.0.27.post2. FA2 = False]\n", - " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", - "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "6e3c281f112b4a86af7a3ef95933d221", - "version_major": 2, - "version_minor": 0 + "cell_type": "markdown", + "metadata": { + "id": "x_wPZgziQKXy" }, - "text/plain": [ - "model.safetensors: 0%| | 0.00/5.70G [00:00\n", + "\n", + "\n", + " Join Discord if you need help + ⭐ Star us on Github ⭐\n", + "\n", + "\n", + "This notebook is an **ASFT / ASFT+ demo** (Anchored Supervised Fine-Tuning).\n", + "\n", + "Credits:\n", + "- ASFT paper & reference implementation: https://github.com/zhuchichi56/ASFT\n", + "- ASFT+ (this optimized Unsloth integration + extra speed/perf optimizations): Can (cansolakoglu130@gmail.com) X/Twitter @HCSolakoglu\n", + "\n", + "To install Unsloth your local device, follow [our guide](https://docs.unsloth.ai/get-started/install-and-update). This notebook is licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).\n", + "\n", + "You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save)\n" ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "ac5eacaaee8346c080e54ea7a52648a4", - "version_major": 2, - "version_minor": 0 + "cell_type": "markdown", + "metadata": { + "id": "t-ahwuyvQKXz" }, - "text/plain": [ - "generation_config.json: 0%| | 0.00/230 [00:00=0.34.0\" hf_transfer\n", + " %pip install --no-deps unsloth\n", + "\n", + "%pip install transformers==4.56.2\n", + "%pip install --no-deps trl==0.22.2" ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "from unsloth import FastLanguageModel\n", - "import torch\n", - "max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!\n", - "dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+\n", - "load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.\n", - "\n", - "# 4bit pre quantized models we support for 4x faster downloading + no OOMs.\n", - "fourbit_models = [\n", - " \"unsloth/Meta-Llama-3.1-8B-bnb-4bit\", # Llama-3.1 15 trillion tokens model 2x faster!\n", - " \"unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit\",\n", - " \"unsloth/Meta-Llama-3.1-70B-bnb-4bit\",\n", - " \"unsloth/Meta-Llama-3.1-405B-bnb-4bit\", # We also uploaded 4bit for 405b!\n", - " \"unsloth/Mistral-Nemo-Base-2407-bnb-4bit\", # New Mistral 12b 2x faster!\n", - " \"unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit\",\n", - " \"unsloth/mistral-7b-v0.3-bnb-4bit\", # Mistral v3 2x faster!\n", - " \"unsloth/mistral-7b-instruct-v0.3-bnb-4bit\",\n", - " \"unsloth/Phi-3.5-mini-instruct\", # Phi-3.5 2x faster!\n", - " \"unsloth/Phi-3-medium-4k-instruct\",\n", - " \"unsloth/gemma-2-9b-bnb-4bit\",\n", - " \"unsloth/gemma-2-27b-bnb-4bit\", # Gemma 2x faster!\n", - "] # More models at https://huggingface.co/unsloth\n", - "\n", - "model, tokenizer = FastLanguageModel.from_pretrained(\n", - " model_name = \"unsloth/Meta-Llama-3.1-8B\",\n", - " max_seq_length = max_seq_length,\n", - " dtype = dtype,\n", - " load_in_4bit = load_in_4bit,\n", - " # token = \"hf_...\", # use one if using gated models like meta-llama/Llama-2-7b-hf\n", - ")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "SXd9bTZd1aaL" - }, - "source": [ - "We now add LoRA adapters so we only need to update 1 to 10% of all parameters!" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" }, - "id": "6bZsfBuZDeCL", - "outputId": "3e2a4618-6aa0-4f1c-d3a0-0ec45eb33237" - }, - "outputs": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "Unsloth 2024.8 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.\n" - ] - } - ], - "source": [ - "model = FastLanguageModel.get_peft_model(\n", - " model,\n", - " r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n", - " target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n", - " \"gate_proj\", \"up_proj\", \"down_proj\",],\n", - " lora_alpha = 16,\n", - " lora_dropout = 0, # Supports any, but = 0 is optimized\n", - " bias = \"none\", # Supports any, but = \"none\" is optimized\n", - " # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n", - " use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n", - " random_state = 3407,\n", - " use_rslora = False, # We support rank stabilized LoRA\n", - " loftq_config = None, # And LoftQ\n", - ")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "vITh0KVJ10qX" - }, - "source": [ - "\n", - "### Data Prep\n", - "We now use the Alpaca dataset from [yahma](https://huggingface.co/datasets/yahma/alpaca-cleaned), which is a filtered version of 52K of the original [Alpaca dataset](https://crfm.stanford.edu/2023/03/13/alpaca.html). You can replace this code section with your own data prep.\n", - "\n", - "**[NOTE]** To train only on completions (ignoring the user's input) read TRL's docs [here](https://huggingface.co/docs/trl/sft_trainer#train-on-completions-only).\n", - "\n", - "**[NOTE]** Remember to add the **EOS_TOKEN** to the tokenized output!! Otherwise you'll get infinite generations!\n", - "\n", - "If you want to use the `llama-3` template for ShareGPT datasets, try our conversational [notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Alpaca.ipynb)\n", - "\n", - "For text completions like novel writing, try this [notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_(7B)-Text_Completion.ipynb)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 145, - "referenced_widgets": [ - "5e8825fb770b41529f2129113cebc4a9", - "0a9dc233674e4096b7a988a5e4ebaf84", - "374fa9beda4042e1bf9a9b13de6e6674", - "e6533d3c91fd4359bc84ffd8e59af5a3", - "f9b01aebcbdc48a585b7942b0ee60a2d", - "d4b3770433bc41818372b7aed243fb31", - "19bcefcc1d874840ae9a9ca983e474b6", - "4011ce9370d74fad857ec8e1e99d314f", - "41f5fed060ad4c8d87b24602b720ef04", - "88fcd51819b5483c9ab22df7ef89ab64", - "e6ffac074f1b476ba2ade11b37732af3", - "98a6716e7438429ea322adb3e3264f91", - "68c686291b50430faeef0de7840e2c4b", - "953625aa1e824f8a8d203197b316b302", - "f899a815142542219bde22ff792fb60c", - "51ca174d26e94b5cb1e895aa3c770655", - "f4519637bb43400a80ce83505101e8a5", - "805676b197c94f5aa45956daa354640b", - "ce9fcc5eff1f460d80b703a4ca32dad1", - "3fef797403d14440afe599a3bf06b626", - "4e7cb8e988114ed4b6fe09ff9f682dff", - "a14bc1c2130842568a5fde6698731e5f", - "85cc6f24cba54563acb5598f54fed7b9", - "80a72037771e4da9be989eefabbc8e76", - "ba68b274c50b44ec9e02642378d271a6", - "f84d2fe4f1c24a34948755abf1f32b7f", - "86511967834f4484a5ec4af387b7d7a9", - "c97c40c2bf2a41a8ae1c75e0a9c8ebff", - "484e507f14424f2b9173595b985f4101", - "68a32b398e1c490393e01befdc260785", - "04cc963133d242779572d2e847fa3d65", - "94730f13e92a4c9aac35c2cfb21fc48c", - "620c0de28ec74f71a021a2be96dccf3a", - "6e1aff64771c402ab070f650562fa4c9", - "0078f897f2174217a307d95d4f9bd775", - "ecdeaab4f8c94d6dade63bb06857c969", - "735b85f0a0e9411cac4d704a504fcfc1", - "8e992e60416145a8b6eed744287ca0fb", - "8c195b5809604905b5e404baa30e8449", - "2247efac4283489bbd228330344388ab", - "e93d063faf984cc4aa51462418d9b57e", - "9d45b9a5de3e4cba9ac35ad2cb187f51", - "e99423a1ed3f4f72886b39368468b7c1", - "5f174718e5974a7cab024d113f662513" - ] - }, - "id": "LjY75GoYUCB8", - "outputId": "80d6c3b9-28c2-4ebf-9c57-6a0b77ce82b1" - }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "5e8825fb770b41529f2129113cebc4a9", - "version_major": 2, - "version_minor": 0 + "cell_type": "markdown", + "metadata": { + "id": "S68-v0avQKX1" }, - "text/plain": [ - "Downloading readme: 0%| | 0.00/11.6k [00:00 0 ! Suggested 8, 16, 32, 64, 128\n", + " target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n", + " \"gate_proj\", \"up_proj\", \"down_proj\",],\n", + " lora_alpha = 16,\n", + " lora_dropout = 0, # Supports any, but = 0 is optimized\n", + " bias = \"none\", # Supports any, but = \"none\" is optimized\n", + " # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n", + " use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n", + " random_state = 3407,\n", + " use_rslora = False, # We support rank stabilized LoRA\n", + " loftq_config = None, # And LoftQ\n", + ")" ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "alpaca_prompt = \"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", - "\n", - "### Instruction:\n", - "{}\n", - "\n", - "### Input:\n", - "{}\n", - "\n", - "### Response:\n", - "{}\"\"\"\n", - "\n", - "EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN\n", - "def formatting_prompts_func(examples):\n", - " instructions = examples[\"instruction\"]\n", - " inputs = examples[\"input\"]\n", - " outputs = examples[\"output\"]\n", - " texts = []\n", - " for instruction, input, output in zip(instructions, inputs, outputs):\n", - " # Must add EOS_TOKEN, otherwise your generation will go on forever!\n", - " text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN\n", - " texts.append(text)\n", - " return { \"text\" : texts, }\n", - "\n", - "from datasets import load_dataset\n", - "dataset = load_dataset(\"yahma/alpaca-cleaned\", split = \"train\")\n", - "dataset = dataset.map(formatting_prompts_func, batched = True,)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "idAEIeSQ3xdS" - }, - "source": [ - "\n", - "### Train the model (ASFT / ASFT+ demo)\n", - "This demo notebook uses **Unsloth `ASFTTrainer`** (Anchored Supervised Fine-Tuning) instead of the standard `SFTTrainer`.\n", - "\n", - "ASFT in a nutshell:\n", - "- Uses **DFT weights** (based on token probabilities / confidence) to reweight token-level CE loss.\n", - "- Adds lightweight **KL anchoring** to stay close to a reference distribution (stability).\n", - "- Supports **streaming** to chunk the reference forward pass and reduce peak VRAM.\n", - "\n", - "**ASFT+** in this repo refers to the same ASFT objective with extra engineering work (performance + VRAM optimizations) on top.\n", - "\n", - "Note: `max_steps` is kept small for a quick demo. For a full run, set `max_steps=None` and use `num_train_epochs=1` (or similar)." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "#### Recommended ASFT defaults (optimized)\n", - "- `asft_mode=\"asft\"` + `kl_weight=0.05`: a solid starting point (stable, not overly restrictive).\n", - "- `reference_policy=\"disable_adapter\"`: avoids keeping a separate frozen reference copy in most PEFT setups.\n", - "- `ASFTStreamingConfig(enabled=True, ref_strategy=\"batch_micro\")`: micro-batches the reference forward pass to reduce peak VRAM.\n", - "\n", - "For quick comparisons, try: `asft_mode=\"sft\"` or `asft_mode=\"dft\"` (KL off)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 67, - "referenced_widgets": [ - "3719bf6f9c6a4c6fbef93c5328c11a07", - "03f492b4b56f4d8e80e9395a65058b1b", - "39d9ef9fb35f47119f319f48eb222070", - "3d7cfb33ceaf417e851ac4393c65148b", - "ece66fa2f128456fa2a82b8a28d1211c", - "9695a640b0ff4e91af495bb59548e4b6", - "d4bd5559d4134d64a943d57972c6ef39", - "fbae6e599d1644f39e5d86efa0f9f997", - "00d425bca350451da6400f9f05c4a659", - "6a27d9ad4f064586a87636b10455d15b", - "77f4367616964a01a8c42416f5f4c147" - ] }, - "id": "95_Nn-89DhsL", - "outputId": "29798478-b975-42d3-b32b-020a805cac35" - }, - "outputs": [ { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "3719bf6f9c6a4c6fbef93c5328c11a07", - "version_major": 2, - "version_minor": 0 + "cell_type": "markdown", + "metadata": { + "id": "vITh0KVJ10qX" }, - "text/plain": [ - "Map (num_proc=2): 0%| | 0/51760 [00:00\n", + "### Data Prep\n", + "We now use the Alpaca dataset from [yahma](https://huggingface.co/datasets/yahma/alpaca-cleaned), which is a filtered version of 52K of the original [Alpaca dataset](https://crfm.stanford.edu/2023/03/13/alpaca.html). You can replace this code section with your own data prep.\n", + "\n", + "**[NOTE]** To train only on completions (ignoring the user's input) read TRL's docs [here](https://huggingface.co/docs/trl/sft_trainer#train-on-completions-only).\n", + "\n", + "**[NOTE]** Remember to add the **EOS_TOKEN** to the tokenized output!! Otherwise you'll get infinite generations!\n", + "\n", + "If you want to use the `llama-3` template for ShareGPT datasets, try our conversational [notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Alpaca.ipynb)\n", + "\n", + "For text completions like novel writing, try this [notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_(7B)-Text_Completion.ipynb)." ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "name": "stderr", - "output_type": "stream", - "text": [ - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - } - ], - "source": [ - "from trl import SFTConfig\n", - "\n", - "try:\n", - " from unsloth.trainer import ASFTTrainer, ASFTStreamingConfig\n", - "except Exception as e:\n", - " raise ImportError(\n", - " \"ASFTTrainer bulunamadı. Bu ASFT demo notebook'u için Unsloth'u bu repo/branch'ten kurun: \"\n", - " \"(lokalde) `pip install -e .` veya (Colab) ilgili git kurulumunu kullanın.\"\n", - " ) from e\n", - "\n", - "# --- ASFT ayarları (demo için optimize varsayılanlar) ---\n", - "asft_mode = \"asft\" # \"sft\" | \"dft\" | \"sft+kl\" | \"asft\"\n", - "kl_weight = 0.05 # KL gücü (\"sft+kl\" ve \"asft\" için)\n", - "reference_policy = \"disable_adapter\" # \"disable_adapter\" | \"frozen_copy\"\n", - "\n", - "# VRAM pikini düşürmek için referans forward streaming\n", - "asft_streaming = ASFTStreamingConfig(\n", - " enabled = True,\n", - " ref_strategy = \"batch_micro\",\n", - " # ref_microbatch_size = 1, # İsterseniz sabitleyin; None ise otomatik seçilir\n", - " force_fp32_kl = True,\n", - ")\n", - "\n", - "trainer = ASFTTrainer(\n", - " model = model,\n", - " tokenizer = tokenizer,\n", - " train_dataset = dataset,\n", - " dataset_text_field = \"text\",\n", - " max_seq_length = max_seq_length,\n", - " packing = True, # Kısa dizilerde hız için True deneyebilirsiniz.\n", - " asft_enabled = True,\n", - " asft_mode = asft_mode,\n", - " kl_weight = kl_weight,\n", - " reference_policy = reference_policy,\n", - " asft_streaming = asft_streaming,\n", - " args = SFTConfig(\n", - " per_device_train_batch_size = 2,\n", - " gradient_accumulation_steps = 4,\n", - " warmup_steps = 5,\n", - " # num_train_epochs = 1, # Tam eğitim için açın.\n", - " max_steps = 60,\n", - " learning_rate = 2e-4,\n", - " logging_steps = 1,\n", - " optim = \"adamw_8bit\",\n", - " weight_decay = 0.001,\n", - " lr_scheduler_type = \"linear\",\n", - " seed = 3407,\n", - " output_dir = \"outputs\",\n", - " report_to = \"none\", # TrackIO/WandB vb.\n", - " ),\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Quick sanity check: confirm ASFT is enabled and configured\n", - "print(\"ASFT enabled:\", getattr(trainer, \"asft_enabled\", None))\n", - "print(\"ASFT mode:\", getattr(trainer, \"asft_mode\", None))\n", - "print(\"KL weight:\", getattr(trainer, \"kl_weight\", None))\n", - "print(\"Reference policy:\", getattr(trainer, \"reference_policy\", None))\n", - "streaming = getattr(trainer, \"asft_streaming\", None)\n", - "if streaming is not None:\n", - " print(\"Streaming enabled:\", getattr(streaming, \"enabled\", None))\n", - " print(\"Streaming strategy:\", getattr(streaming, \"ref_strategy\", None))" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "cellView": "form", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "2ejIt2xSNKKp", - "outputId": "d397dd48-304c-4f42-ecbc-d5c9ce14989c" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "GPU = Tesla T4. Max memory = 14.748 GB.\n", - "5.984 GB of memory reserved.\n" - ] - } - ], - "source": [ - "# @title Show current memory stats\n", - "gpu_stats = torch.cuda.get_device_properties(0)\n", - "start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", - "max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)\n", - "print(f\"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.\")\n", - "print(f\"{start_gpu_memory} GB of memory reserved.\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 1000 - }, - "id": "yqxqAZ7KJ4oL", - "outputId": "76534fb4-5f9a-4da4-9740-fcff4583fd1c" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", - " \\\\ /| Num examples = 51,760 | Num Epochs = 1\n", - "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", - "\\ / Total batch size = 8 | Total steps = 60\n", - " \"-____-\" Number of trainable parameters = 41,943,040\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [60/60 07:28, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining Loss
11.817600
22.304200
31.689300
41.938200
51.656900
61.621900
71.187100
81.264200
91.101200
101.189500
110.930800
120.959400
130.929400
141.048700
150.892800
160.901400
171.009100
181.256100
191.016500
200.882600
210.940500
221.018500
230.897200
240.991900
251.072000
261.022900
271.044900
280.877800
290.843800
300.887500
310.853400
320.866000
330.983200
340.852200
350.961200
360.856700
370.872300
380.751100
391.081400
401.174400
410.893400
420.977500
430.957100
440.908100
450.915000
460.973400
470.870900
481.196500
490.907500
501.031300
511.015900
520.907900
530.977000
541.154300
550.778000
561.013300
570.886800
580.827500
590.852300
600.896600

" + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 145, + "referenced_widgets": [ + "5e8825fb770b41529f2129113cebc4a9", + "0a9dc233674e4096b7a988a5e4ebaf84", + "374fa9beda4042e1bf9a9b13de6e6674", + "e6533d3c91fd4359bc84ffd8e59af5a3", + "f9b01aebcbdc48a585b7942b0ee60a2d", + "d4b3770433bc41818372b7aed243fb31", + "19bcefcc1d874840ae9a9ca983e474b6", + "4011ce9370d74fad857ec8e1e99d314f", + "41f5fed060ad4c8d87b24602b720ef04", + "88fcd51819b5483c9ab22df7ef89ab64", + "e6ffac074f1b476ba2ade11b37732af3", + "98a6716e7438429ea322adb3e3264f91", + "68c686291b50430faeef0de7840e2c4b", + "953625aa1e824f8a8d203197b316b302", + "f899a815142542219bde22ff792fb60c", + "51ca174d26e94b5cb1e895aa3c770655", + "f4519637bb43400a80ce83505101e8a5", + "805676b197c94f5aa45956daa354640b", + "ce9fcc5eff1f460d80b703a4ca32dad1", + "3fef797403d14440afe599a3bf06b626", + "4e7cb8e988114ed4b6fe09ff9f682dff", + "a14bc1c2130842568a5fde6698731e5f", + "85cc6f24cba54563acb5598f54fed7b9", + "80a72037771e4da9be989eefabbc8e76", + "ba68b274c50b44ec9e02642378d271a6", + "f84d2fe4f1c24a34948755abf1f32b7f", + "86511967834f4484a5ec4af387b7d7a9", + "c97c40c2bf2a41a8ae1c75e0a9c8ebff", + "484e507f14424f2b9173595b985f4101", + "68a32b398e1c490393e01befdc260785", + "04cc963133d242779572d2e847fa3d65", + "94730f13e92a4c9aac35c2cfb21fc48c", + "620c0de28ec74f71a021a2be96dccf3a", + "6e1aff64771c402ab070f650562fa4c9", + "0078f897f2174217a307d95d4f9bd775", + "ecdeaab4f8c94d6dade63bb06857c969", + "735b85f0a0e9411cac4d704a504fcfc1", + "8e992e60416145a8b6eed744287ca0fb", + "8c195b5809604905b5e404baa30e8449", + "2247efac4283489bbd228330344388ab", + "e93d063faf984cc4aa51462418d9b57e", + "9d45b9a5de3e4cba9ac35ad2cb187f51", + "e99423a1ed3f4f72886b39368468b7c1", + "5f174718e5974a7cab024d113f662513" + ] + }, + "id": "LjY75GoYUCB8", + "outputId": "80d6c3b9-28c2-4ebf-9c57-6a0b77ce82b1" + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "5e8825fb770b41529f2129113cebc4a9", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Downloading readme: 0%| | 0.00/11.6k [00:00" + "source": [ + "alpaca_prompt = \"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", + "\n", + "### Instruction:\n", + "{}\n", + "\n", + "### Input:\n", + "{}\n", + "\n", + "### Response:\n", + "{}\"\"\"\n", + "\n", + "EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN\n", + "def formatting_prompts_func(examples):\n", + " instructions = examples[\"instruction\"]\n", + " inputs = examples[\"input\"]\n", + " outputs = examples[\"output\"]\n", + " texts = []\n", + " for instruction, input, output in zip(instructions, inputs, outputs):\n", + " # Must add EOS_TOKEN, otherwise your generation will go on forever!\n", + " text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN\n", + " texts.append(text)\n", + " return { \"text\" : texts, }\n", + "\n", + "from datasets import load_dataset\n", + "dataset = load_dataset(\"yahma/alpaca-cleaned\", split = \"train\")\n", + "dataset = dataset.map(formatting_prompts_func, batched = True,)" ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "trainer_stats = trainer.train()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "cellView": "form", - "colab": { - "base_uri": "https://localhost:8080/" }, - "id": "pCqnaKmlO1U9", - "outputId": "edf33a96-b12c-4bba-9771-59e18aee707c" - }, - "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "462.7198 seconds used for training.\n", - "7.71 minutes used for training.\n", - "Peak reserved memory = 7.922 GB.\n", - "Peak reserved memory for training = 1.938 GB.\n", - "Peak reserved memory % of max memory = 53.716 %.\n", - "Peak reserved memory for training % of max memory = 13.141 %.\n" - ] - } - ], - "source": [ - "# @title Show final memory and time stats\n", - "used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", - "used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n", - "used_percentage = round(used_memory / max_memory * 100, 3)\n", - "lora_percentage = round(used_memory_for_lora / max_memory * 100, 3)\n", - "print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n", - "print(\n", - " f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\"\n", - ")\n", - "print(f\"Peak reserved memory = {used_memory} GB.\")\n", - "print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n", - "print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n", - "print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ekOmTR1hSNcr" - }, - "source": [ - "\n", - "### Inference\n", - "Let's run the model! You can change the instruction and input - leave the output blank!\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "kR3gIAX-SM2q", - "outputId": "087c5c13-e946-4c35-e4f2-e07a88f9ac32" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "['<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nContinue the fibonnaci sequence.\\n\\n### Input:\\n1, 1, 2, 3, 5, 8\\n\\n### Response:\\n13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025']" + "cell_type": "markdown", + "metadata": { + "id": "idAEIeSQ3xdS" + }, + "source": [ + "\n", + "### Train the model (ASFT / ASFT+ demo)\n", + "This demo notebook uses **Unsloth `ASFTTrainer`** (Anchored Supervised Fine-Tuning) instead of the standard `SFTTrainer`.\n", + "\n", + "ASFT in a nutshell:\n", + "- Uses **DFT weights** (based on token probabilities / confidence) to reweight token-level CE loss.\n", + "- Adds lightweight **KL anchoring** to stay close to a reference distribution (stability).\n", + "- Supports **streaming** to chunk the reference forward pass and reduce peak VRAM.\n", + "\n", + "**ASFT+** in this repo refers to the same ASFT objective with extra engineering work (performance + VRAM optimizations) on top.\n", + "\n", + "Note: `max_steps` is kept small for a quick demo. For a full run, set `max_steps=None` and use `num_train_epochs=1` (or similar)." ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# alpaca_prompt = Copied from above\n", - "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", - "inputs = tokenizer(\n", - "[\n", - " alpaca_prompt.format(\n", - " \"Continue the fibonnaci sequence.\", # instruction\n", - " \"1, 1, 2, 3, 5, 8\", # input\n", - " \"\", # output - leave this blank for generation!\n", - " )\n", - "], return_tensors = \"pt\").to(\"cuda\")\n", - "\n", - "outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)\n", - "tokenizer.batch_decode(outputs)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "CrSvZObor0lY" - }, - "source": [ - " You can also use a `TextStreamer` for continuous inference - so you can see the generation token by token, instead of waiting the whole time!" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" }, - "id": "e2pEuRb1r2Vg", - "outputId": "b13f5e53-4ca4-4551-dffa-aaa3c514dca4" - }, - "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", - "\n", - "### Instruction:\n", - "Continue the fibonnaci sequence.\n", - "\n", - "### Input:\n", - "1, 1, 2, 3, 5, 8\n", - "\n", - "### Response:\n", - "13, 21, 34, 55, 89, 144<|end_of_text|>\n" - ] - } - ], - "source": [ - "# alpaca_prompt = Copied from above\n", - "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", - "inputs = tokenizer(\n", - "[\n", - " alpaca_prompt.format(\n", - " \"Continue the fibonnaci sequence.\", # instruction\n", - " \"1, 1, 2, 3, 5, 8\", # input\n", - " \"\", # output - leave this blank for generation!\n", - " )\n", - "], return_tensors = \"pt\").to(\"cuda\")\n", - "\n", - "from transformers import TextStreamer\n", - "text_streamer = TextStreamer(tokenizer)\n", - "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "uMuVrWbjAzhc" - }, - "source": [ - "\n", - "### Saving, loading finetuned models\n", - "To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.\n", - "\n", - "**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "upcOlWe7A1vc", - "outputId": "030a6e13-9371-4717-c5c5-d4e3563e0cca" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "('lora_model/tokenizer_config.json',\n", - " 'lora_model/special_tokens_map.json',\n", - " 'lora_model/tokenizer.json')" + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Recommended ASFT defaults (optimized)\n", + "- `asft_mode=\"asft\"` + `kl_weight=0.05`: a solid starting point (stable, not overly restrictive).\n", + "- `reference_policy=\"disable_adapter\"`: avoids keeping a separate frozen reference copy in most PEFT setups.\n", + "- `ASFTStreamingConfig(enabled=True, ref_strategy=\"batch_micro\")`: micro-batches the reference forward pass to reduce peak VRAM.\n", + "\n", + "For quick comparisons, try: `asft_mode=\"sft\"` or `asft_mode=\"dft\"` (KL off)." ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "model.save_pretrained(\"lora_model\") # Local saving\n", - "tokenizer.save_pretrained(\"lora_model\")\n", - "# model.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving\n", - "# tokenizer.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "AEEcJ4qfC7Lp" - }, - "source": [ - "Now if you want to load the LoRA adapters we just saved for inference, set `False` to `True`:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" }, - "id": "MKX_XKs_BNZR", - "outputId": "f8e7d3fe-8e4d-49ee-944f-08e70cdc1d87" - }, - "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", - "\n", - "### Instruction:\n", - "What is a famous tall tower in Paris?\n", - "\n", - "### Input:\n", - "\n", - "\n", - "### Response:\n", - "One of the most famous and iconic tall towers in Paris is the Eiffel Tower. Standing at 324 meters (1,063 feet) tall, this wrought iron tower is a symbol of the city and a must-see attraction for tourists from all over the world.<|end_of_text|>\n" - ] + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 67, + "referenced_widgets": [ + "3719bf6f9c6a4c6fbef93c5328c11a07", + "03f492b4b56f4d8e80e9395a65058b1b", + "39d9ef9fb35f47119f319f48eb222070", + "3d7cfb33ceaf417e851ac4393c65148b", + "ece66fa2f128456fa2a82b8a28d1211c", + "9695a640b0ff4e91af495bb59548e4b6", + "d4bd5559d4134d64a943d57972c6ef39", + "fbae6e599d1644f39e5d86efa0f9f997", + "00d425bca350451da6400f9f05c4a659", + "6a27d9ad4f064586a87636b10455d15b", + "77f4367616964a01a8c42416f5f4c147" + ] + }, + "id": "95_Nn-89DhsL", + "outputId": "29798478-b975-42d3-b32b-020a805cac35" + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "3719bf6f9c6a4c6fbef93c5328c11a07", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Map (num_proc=2): 0%| | 0/51760 [00:00\n", + " \n", + " \n", + " [60/60 07:28, Epoch 0/1]\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
StepTraining Loss
11.817600
22.304200
31.689300
41.938200
51.656900
61.621900
71.187100
81.264200
91.101200
101.189500
110.930800
120.959400
130.929400
141.048700
150.892800
160.901400
171.009100
181.256100
191.016500
200.882600
210.940500
221.018500
230.897200
240.991900
251.072000
261.022900
271.044900
280.877800
290.843800
300.887500
310.853400
320.866000
330.983200
340.852200
350.961200
360.856700
370.872300
380.751100
391.081400
401.174400
410.893400
420.977500
430.957100
440.908100
450.915000
460.973400
470.870900
481.196500
490.907500
501.031300
511.015900
520.907900
530.977000
541.154300
550.778000
561.013300
570.886800
580.827500
590.852300
600.896600

" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "trainer_stats = trainer.train()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "cellView": "form", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "pCqnaKmlO1U9", + "outputId": "edf33a96-b12c-4bba-9771-59e18aee707c" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "462.7198 seconds used for training.\n", + "7.71 minutes used for training.\n", + "Peak reserved memory = 7.922 GB.\n", + "Peak reserved memory for training = 1.938 GB.\n", + "Peak reserved memory % of max memory = 53.716 %.\n", + "Peak reserved memory for training % of max memory = 13.141 %.\n" + ] + } + ], + "source": [ + "# @title Show final memory and time stats\n", + "used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", + "used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n", + "used_percentage = round(used_memory / max_memory * 100, 3)\n", + "lora_percentage = round(used_memory_for_lora / max_memory * 100, 3)\n", + "print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n", + "print(\n", + " f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\"\n", + ")\n", + "print(f\"Peak reserved memory = {used_memory} GB.\")\n", + "print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n", + "print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n", + "print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ekOmTR1hSNcr" + }, + "source": [ + "\n", + "### Inference\n", + "Let's run the model! You can change the instruction and input - leave the output blank!\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "kR3gIAX-SM2q", + "outputId": "087c5c13-e946-4c35-e4f2-e07a88f9ac32" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "['<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nContinue the fibonnaci sequence.\\n\\n### Input:\\n1, 1, 2, 3, 5, 8\\n\\n### Response:\\n13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025']" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# alpaca_prompt = Copied from above\n", + "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", + "inputs = tokenizer(\n", + "[\n", + " alpaca_prompt.format(\n", + " \"Continue the fibonnaci sequence.\", # instruction\n", + " \"1, 1, 2, 3, 5, 8\", # input\n", + " \"\", # output - leave this blank for generation!\n", + " )\n", + "], return_tensors = \"pt\").to(\"cuda\")\n", + "\n", + "outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)\n", + "tokenizer.batch_decode(outputs)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "CrSvZObor0lY" + }, + "source": [ + " You can also use a `TextStreamer` for continuous inference - so you can see the generation token by token, instead of waiting the whole time!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "e2pEuRb1r2Vg", + "outputId": "b13f5e53-4ca4-4551-dffa-aaa3c514dca4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", + "\n", + "### Instruction:\n", + "Continue the fibonnaci sequence.\n", + "\n", + "### Input:\n", + "1, 1, 2, 3, 5, 8\n", + "\n", + "### Response:\n", + "13, 21, 34, 55, 89, 144<|end_of_text|>\n" + ] + } + ], + "source": [ + "# alpaca_prompt = Copied from above\n", + "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", + "inputs = tokenizer(\n", + "[\n", + " alpaca_prompt.format(\n", + " \"Continue the fibonnaci sequence.\", # instruction\n", + " \"1, 1, 2, 3, 5, 8\", # input\n", + " \"\", # output - leave this blank for generation!\n", + " )\n", + "], return_tensors = \"pt\").to(\"cuda\")\n", + "\n", + "from transformers import TextStreamer\n", + "text_streamer = TextStreamer(tokenizer)\n", + "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uMuVrWbjAzhc" + }, + "source": [ + "\n", + "### Saving, loading finetuned models\n", + "To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.\n", + "\n", + "**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "upcOlWe7A1vc", + "outputId": "030a6e13-9371-4717-c5c5-d4e3563e0cca" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "('lora_model/tokenizer_config.json',\n", + " 'lora_model/special_tokens_map.json',\n", + " 'lora_model/tokenizer.json')" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model.save_pretrained(\"lora_model\") # Local saving\n", + "tokenizer.save_pretrained(\"lora_model\")\n", + "# model.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving\n", + "# tokenizer.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "AEEcJ4qfC7Lp" + }, + "source": [ + "Now if you want to load the LoRA adapters we just saved for inference, set `False` to `True`:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "MKX_XKs_BNZR", + "outputId": "f8e7d3fe-8e4d-49ee-944f-08e70cdc1d87" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", + "\n", + "### Instruction:\n", + "What is a famous tall tower in Paris?\n", + "\n", + "### Input:\n", + "\n", + "\n", + "### Response:\n", + "One of the most famous and iconic tall towers in Paris is the Eiffel Tower. Standing at 324 meters (1,063 feet) tall, this wrought iron tower is a symbol of the city and a must-see attraction for tourists from all over the world.<|end_of_text|>\n" + ] + } + ], + "source": [ + "if False:\n", + " from unsloth import FastLanguageModel\n", + " model, tokenizer = FastLanguageModel.from_pretrained(\n", + " model_name = \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", + " max_seq_length = max_seq_length,\n", + " dtype = dtype,\n", + " load_in_4bit = load_in_4bit,\n", + " )\n", + " FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", + "\n", + "# alpaca_prompt = You MUST copy from above!\n", + "\n", + "inputs = tokenizer(\n", + "[\n", + " alpaca_prompt.format(\n", + " \"What is a famous tall tower in Paris?\", # instruction\n", + " \"\", # input\n", + " \"\", # output - leave this blank for generation!\n", + " )\n", + "], return_tensors = \"pt\").to(\"cuda\")\n", + "\n", + "from transformers import TextStreamer\n", + "text_streamer = TextStreamer(tokenizer)\n", + "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QQMjaNrjsU5_" + }, + "source": [ + "You can also use Hugging Face's `AutoModelForPeftCausalLM`. Only use this if you do not have `unsloth` installed. It can be hopelessly slow, since `4bit` model downloading is not supported, and Unsloth's **inference is 2x faster**." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "yFfaXG0WsQuE" + }, + "outputs": [], + "source": [ + "if False:\n", + " # I highly do NOT suggest - use Unsloth if possible\n", + " from peft import AutoPeftModelForCausalLM\n", + " from transformers import AutoTokenizer\n", + " model = AutoPeftModelForCausalLM.from_pretrained(\n", + " \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", + " load_in_4bit = load_in_4bit,\n", + " )\n", + " tokenizer = AutoTokenizer.from_pretrained(\"lora_model\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f422JgM9sdVT" + }, + "source": [ + "### Saving to float16 for VLLM\n", + "\n", + "We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "iHjt_SMYsd3P" + }, + "outputs": [], + "source": [ + "# Merge to 16bit\n", + "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n", + "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n", + "\n", + "# Merge to 4bit\n", + "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n", + "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n", + "\n", + "# Just LoRA adapters\n", + "if False:\n", + " model.save_pretrained(\"model\")\n", + " tokenizer.save_pretrained(\"model\")\n", + "if False:\n", + " model.push_to_hub(\"hf/model\", token = \"\")\n", + " tokenizer.push_to_hub(\"hf/model\", token = \"\")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "TCv4vXHd61i7" + }, + "source": [ + "### GGUF / llama.cpp Conversion\n", + "To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.\n", + "\n", + "Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):\n", + "* `q8_0` - Fast conversion. High resource use, but generally acceptable.\n", + "* `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.\n", + "* `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.\n", + "\n", + "[**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "FqfebeAdT073" + }, + "outputs": [], + "source": [ + "# Save to 8bit Q8_0\n", + "if False: model.save_pretrained_gguf(\"model\", tokenizer,)\n", + "# Remember to go to https://huggingface.co/settings/tokens for a token!\n", + "# And change hf to your username!\n", + "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, token = \"\")\n", + "\n", + "# Save to 16bit GGUF\n", + "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"f16\")\n", + "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"f16\", token = \"\")\n", + "\n", + "# Save to q4_k_m GGUF\n", + "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"q4_k_m\")\n", + "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"q4_k_m\", token = \"\")\n", + "\n", + "# Save to multiple GGUF options - much faster if you want multiple!\n", + "if False:\n", + " model.push_to_hub_gguf(\n", + " \"hf/model\", # Change hf to your username!\n", + " tokenizer,\n", + " quantization_method = [\"q4_k_m\", \"q8_0\", \"q5_k_m\",],\n", + " token = \"\",\n", + " )" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kGbBSRn6QKX7" + }, + "source": [ + "Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in llama.cpp.\n", + "\n", + "And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n", + "\n", + "Some other links:\n", + "1. Train your own reasoning model - Llama GRPO notebook [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb)\n", + "2. Saving finetunes to Ollama. [Free notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)\n", + "3. Llama 3.2 Vision finetuning - Radiography use case. [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)\n", + "6. See notebooks for DPO, ORPO, Continued pretraining, conversational finetuning and more on our [documentation](https://docs.unsloth.ai/get-started/unsloth-notebooks)!\n", + "\n", + "

\n", + " \n", + " \n", + " \n", + "\n", + " Join Discord if you need help + ⭐️ Star us on Github ⭐️\n", + "\n", + " This notebook and all Unsloth notebooks are licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).\n", + "
\n" + ] } - ], - "source": [ - "if False:\n", - " from unsloth import FastLanguageModel\n", - " model, tokenizer = FastLanguageModel.from_pretrained(\n", - " model_name = \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", - " max_seq_length = max_seq_length,\n", - " dtype = dtype,\n", - " load_in_4bit = load_in_4bit,\n", - " )\n", - " FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", - "\n", - "# alpaca_prompt = You MUST copy from above!\n", - "\n", - "inputs = tokenizer(\n", - "[\n", - " alpaca_prompt.format(\n", - " \"What is a famous tall tower in Paris?\", # instruction\n", - " \"\", # input\n", - " \"\", # output - leave this blank for generation!\n", - " )\n", - "], return_tensors = \"pt\").to(\"cuda\")\n", - "\n", - "from transformers import TextStreamer\n", - "text_streamer = TextStreamer(tokenizer)\n", - "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "QQMjaNrjsU5_" - }, - "source": [ - "You can also use Hugging Face's `AutoModelForPeftCausalLM`. Only use this if you do not have `unsloth` installed. It can be hopelessly slow, since `4bit` model downloading is not supported, and Unsloth's **inference is 2x faster**." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "yFfaXG0WsQuE" - }, - "outputs": [], - "source": [ - "if False:\n", - " # I highly do NOT suggest - use Unsloth if possible\n", - " from peft import AutoPeftModelForCausalLM\n", - " from transformers import AutoTokenizer\n", - " model = AutoPeftModelForCausalLM.from_pretrained(\n", - " \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", - " load_in_4bit = load_in_4bit,\n", - " )\n", - " tokenizer = AutoTokenizer.from_pretrained(\"lora_model\")" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f422JgM9sdVT" - }, - "source": [ - "### Saving to float16 for VLLM\n", - "\n", - "We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "iHjt_SMYsd3P" - }, - "outputs": [], - "source": [ - "# Merge to 16bit\n", - "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n", - "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n", - "\n", - "# Merge to 4bit\n", - "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n", - "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n", - "\n", - "# Just LoRA adapters\n", - "if False:\n", - " model.save_pretrained(\"model\")\n", - " tokenizer.save_pretrained(\"model\")\n", - "if False:\n", - " model.push_to_hub(\"hf/model\", token = \"\")\n", - " tokenizer.push_to_hub(\"hf/model\", token = \"\")\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "TCv4vXHd61i7" - }, - "source": [ - "### GGUF / llama.cpp Conversion\n", - "To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.\n", - "\n", - "Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):\n", - "* `q8_0` - Fast conversion. High resource use, but generally acceptable.\n", - "* `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.\n", - "* `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.\n", - "\n", - "[**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "FqfebeAdT073" - }, - "outputs": [], - "source": [ - "# Save to 8bit Q8_0\n", - "if False: model.save_pretrained_gguf(\"model\", tokenizer,)\n", - "# Remember to go to https://huggingface.co/settings/tokens for a token!\n", - "# And change hf to your username!\n", - "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, token = \"\")\n", - "\n", - "# Save to 16bit GGUF\n", - "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"f16\")\n", - "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"f16\", token = \"\")\n", - "\n", - "# Save to q4_k_m GGUF\n", - "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"q4_k_m\")\n", - "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"q4_k_m\", token = \"\")\n", - "\n", - "# Save to multiple GGUF options - much faster if you want multiple!\n", - "if False:\n", - " model.push_to_hub_gguf(\n", - " \"hf/model\", # Change hf to your username!\n", - " tokenizer,\n", - " quantization_method = [\"q4_k_m\", \"q8_0\", \"q5_k_m\",],\n", - " token = \"\",\n", - " )" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "kGbBSRn6QKX7" - }, - "source": [ - "Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in llama.cpp.\n", - "\n", - "And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n", - "\n", - "Some other links:\n", - "1. Train your own reasoning model - Llama GRPO notebook [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb)\n", - "2. Saving finetunes to Ollama. [Free notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)\n", - "3. Llama 3.2 Vision finetuning - Radiography use case. [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)\n", - "6. See notebooks for DPO, ORPO, Continued pretraining, conversational finetuning and more on our [documentation](https://docs.unsloth.ai/get-started/unsloth-notebooks)!\n", - "\n", - "
\n", - " \n", - " \n", - " \n", - "\n", - " Join Discord if you need help + ⭐️ Star us on Github ⭐️\n", - "\n", - " This notebook and all Unsloth notebooks are licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).\n", - "
\n" - ] - } - ], - "metadata": { - "accelerator": "GPU", - "colab": { - "gpuType": "T4", - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "name": "python" - }, - "widgets": { - "application/vnd.jupyter.widget-state+json": { - "0078f897f2174217a307d95d4f9bd775": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8c195b5809604905b5e404baa30e8449", - "placeholder": "​", - "style": "IPY_MODEL_2247efac4283489bbd228330344388ab", - "value": "Map: 100%" - } - }, - "00d425bca350451da6400f9f05c4a659": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "03f492b4b56f4d8e80e9395a65058b1b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_9695a640b0ff4e91af495bb59548e4b6", - "placeholder": "​", - "style": "IPY_MODEL_d4bd5559d4134d64a943d57972c6ef39", - "value": "Map (num_proc=2): 100%" - } - }, - "04cc963133d242779572d2e847fa3d65": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "07055fc12b0841aaa5317f8252b5d347": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "0a9dc233674e4096b7a988a5e4ebaf84": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d4b3770433bc41818372b7aed243fb31", - "placeholder": "​", - "style": "IPY_MODEL_19bcefcc1d874840ae9a9ca983e474b6", - "value": "Downloading readme: 100%" - } - }, - "0c1835f404db4846bb13b5da8d8f4447": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "19bcefcc1d874840ae9a9ca983e474b6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "1a6db9aea6a64ae3aaef51d6265b35b2": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "1bd75ddaf57c4438a4e2c3070b9cef65": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_a3a3ef6d6337403cabea8b23f7c3021b", - "IPY_MODEL_c2ea0a3f01f34ffa8c94ab9b5098e9da", - "IPY_MODEL_68ea1d7cb8274a639b3fb5326f4218c3" - ], - "layout": "IPY_MODEL_39fef7b257614a0595f39355fa226b69" - } - }, - "1c7bc5fdb7dd4c39af8d4c2c504ec3ed": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_843a27e619534ea8914f9d36386c364b", - "IPY_MODEL_8f5adc70fbf248f2811527f620553be5", - "IPY_MODEL_4ffb4b2f015046fb94c1115ed0397a20" - ], - "layout": "IPY_MODEL_5a232ed040f94633a2a374031284c1f6" - } - }, - "1eb90e686e214122ae763b1b79ae321d": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "2006be31c09349738e221295bb84939f": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "2247efac4283489bbd228330344388ab": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "29c5b713f07043dda51820523e5c8ff3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_d7375f0f048841b29a20601c122666e8", - "IPY_MODEL_f433ced9bfcd4a57ba691d3c1caeed08", - "IPY_MODEL_da8ffc70820a48f5a12c6d4b5967015b" - ], - "layout": "IPY_MODEL_1a6db9aea6a64ae3aaef51d6265b35b2" - } - }, - "2b848e5a85bc42bc87945fd9ed5db038": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_bb9f3379310d4b04be694996f3137b28", - "max": 230, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_75082ba15db445df907f5612976590ae", - "value": 230 - } - }, - "2be29a4553ad4dfea8a9bc620c81a3ae": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "331f516c7a76456d801bc2a2feb228aa": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "33843107b93647b28985bfc37ea781ca": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "3662f1445ef34a50b462e601ed31bb69": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "36799fbcd90d43128620ff98225a825d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "3719bf6f9c6a4c6fbef93c5328c11a07": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_03f492b4b56f4d8e80e9395a65058b1b", - "IPY_MODEL_39d9ef9fb35f47119f319f48eb222070", - "IPY_MODEL_3d7cfb33ceaf417e851ac4393c65148b" - ], - "layout": "IPY_MODEL_ece66fa2f128456fa2a82b8a28d1211c" - } - }, - "374fa9beda4042e1bf9a9b13de6e6674": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4011ce9370d74fad857ec8e1e99d314f", - "max": 11610, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_41f5fed060ad4c8d87b24602b720ef04", - "value": 11610 - } - }, - "39d9ef9fb35f47119f319f48eb222070": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_fbae6e599d1644f39e5d86efa0f9f997", - "max": 51760, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_00d425bca350451da6400f9f05c4a659", - "value": 51760 - } - }, - "39fef7b257614a0595f39355fa226b69": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "3d7cfb33ceaf417e851ac4393c65148b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_6a27d9ad4f064586a87636b10455d15b", - "placeholder": "​", - "style": "IPY_MODEL_77f4367616964a01a8c42416f5f4c147", - "value": " 51760/51760 [00:50<00:00, 1965.57 examples/s]" - } - }, - "3fef797403d14440afe599a3bf06b626": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "4011ce9370d74fad857ec8e1e99d314f": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "41f5fed060ad4c8d87b24602b720ef04": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "4228734651ca45e19fc7bda79817f9b3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_f878c2e00bc240c7b0333cce950080e1", - "placeholder": "​", - "style": "IPY_MODEL_6b908368de51428585552dfef6a83088", - "value": " 5.70G/5.70G [00:45<00:00, 645MB/s]" - } - }, - "4613edbbec6846edb5b1677c25d542b6": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "484e507f14424f2b9173595b985f4101": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "4e7cb8e988114ed4b6fe09ff9f682dff": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "4ffb4b2f015046fb94c1115ed0397a20": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8653acb618ad4e76bbf1daa00ea71238", - "placeholder": "​", - "style": "IPY_MODEL_e3c3bd9c4c124b0a8c88c83c1fc747d3", - "value": " 50.6k/50.6k [00:00<00:00, 2.29MB/s]" - } - }, - "51ca174d26e94b5cb1e895aa3c770655": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "51cd9026b1664819a67712996ca97bd5": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "5310346dd579424fa676b8e8e64790e7": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "5a232ed040f94633a2a374031284c1f6": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "5e8825fb770b41529f2129113cebc4a9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_0a9dc233674e4096b7a988a5e4ebaf84", - "IPY_MODEL_374fa9beda4042e1bf9a9b13de6e6674", - "IPY_MODEL_e6533d3c91fd4359bc84ffd8e59af5a3" - ], - "layout": "IPY_MODEL_f9b01aebcbdc48a585b7942b0ee60a2d" - } - }, - "5f174718e5974a7cab024d113f662513": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "620c0de28ec74f71a021a2be96dccf3a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "634ae4c6cfe04673b1cdc9c9cac4cbf9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "68a32b398e1c490393e01befdc260785": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "68c686291b50430faeef0de7840e2c4b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_f4519637bb43400a80ce83505101e8a5", - "placeholder": "​", - "style": "IPY_MODEL_805676b197c94f5aa45956daa354640b", - "value": "Downloading data: 100%" - } - }, - "68ea1d7cb8274a639b3fb5326f4218c3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_5310346dd579424fa676b8e8e64790e7", - "placeholder": "​", - "style": "IPY_MODEL_0c1835f404db4846bb13b5da8d8f4447", - "value": " 9.09M/9.09M [00:00<00:00, 17.1MB/s]" - } - }, - "6a27d9ad4f064586a87636b10455d15b": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "6b908368de51428585552dfef6a83088": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "6e1aff64771c402ab070f650562fa4c9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_0078f897f2174217a307d95d4f9bd775", - "IPY_MODEL_ecdeaab4f8c94d6dade63bb06857c969", - "IPY_MODEL_735b85f0a0e9411cac4d704a504fcfc1" - ], - "layout": "IPY_MODEL_8e992e60416145a8b6eed744287ca0fb" - } - }, - "6e3c281f112b4a86af7a3ef95933d221": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_92395f250a154006923aaf9ea0a9c30b", - "IPY_MODEL_f84bfc5390054ec687c157c4d68199a6", - "IPY_MODEL_4228734651ca45e19fc7bda79817f9b3" - ], - "layout": "IPY_MODEL_4613edbbec6846edb5b1677c25d542b6" - } - }, - "735b85f0a0e9411cac4d704a504fcfc1": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_e99423a1ed3f4f72886b39368468b7c1", - "placeholder": "​", - "style": "IPY_MODEL_5f174718e5974a7cab024d113f662513", - "value": " 51760/51760 [00:00<00:00, 52999.05 examples/s]" - } - }, - "75082ba15db445df907f5612976590ae": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "76e5410e286a4a5abd6c213a38aa38bb": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "77f4367616964a01a8c42416f5f4c147": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "7981edf408d54d41bbeac42da7492c6b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_76e5410e286a4a5abd6c213a38aa38bb", - "placeholder": "​", - "style": "IPY_MODEL_ae7e90a811f94e75997d6a9ed1be8596", - "value": "generation_config.json: 100%" - } - }, - "7a935956348e47c68fbdf05ddf4752f3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "805676b197c94f5aa45956daa354640b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "80a72037771e4da9be989eefabbc8e76": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_c97c40c2bf2a41a8ae1c75e0a9c8ebff", - "placeholder": "​", - "style": "IPY_MODEL_484e507f14424f2b9173595b985f4101", - "value": "Generating train split: 100%" - } - }, - "843a27e619534ea8914f9d36386c364b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_2006be31c09349738e221295bb84939f", - "placeholder": "​", - "style": "IPY_MODEL_07055fc12b0841aaa5317f8252b5d347", - "value": "tokenizer_config.json: 100%" - } - }, - "85cc6f24cba54563acb5598f54fed7b9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_80a72037771e4da9be989eefabbc8e76", - "IPY_MODEL_ba68b274c50b44ec9e02642378d271a6", - "IPY_MODEL_f84d2fe4f1c24a34948755abf1f32b7f" - ], - "layout": "IPY_MODEL_86511967834f4484a5ec4af387b7d7a9" - } - }, - "86511967834f4484a5ec4af387b7d7a9": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "8653acb618ad4e76bbf1daa00ea71238": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "88fcd51819b5483c9ab22df7ef89ab64": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "89934c4f26834f15b9889ec36fee3b65": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "8c195b5809604905b5e404baa30e8449": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "8e992e60416145a8b6eed744287ca0fb": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "8ea52b105a7e44978caca33c0e7e815b": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "8f5adc70fbf248f2811527f620553be5": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_1eb90e686e214122ae763b1b79ae321d", - "max": 50570, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_7a935956348e47c68fbdf05ddf4752f3", - "value": 50570 - } - }, - "92395f250a154006923aaf9ea0a9c30b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d032fe2ba5d647d99026fdade758c0cd", - "placeholder": "​", - "style": "IPY_MODEL_e9971d220fe24552a1e9aa299765cfb9", - "value": "model.safetensors: 100%" - } - }, - "94730f13e92a4c9aac35c2cfb21fc48c": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "94cbb87829d1486899e2ff6325c2ecdf": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "953625aa1e824f8a8d203197b316b302": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_ce9fcc5eff1f460d80b703a4ca32dad1", - "max": 44307561, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_3fef797403d14440afe599a3bf06b626", - "value": 44307561 - } - }, - "9695a640b0ff4e91af495bb59548e4b6": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "98a6716e7438429ea322adb3e3264f91": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_68c686291b50430faeef0de7840e2c4b", - "IPY_MODEL_953625aa1e824f8a8d203197b316b302", - "IPY_MODEL_f899a815142542219bde22ff792fb60c" - ], - "layout": "IPY_MODEL_51ca174d26e94b5cb1e895aa3c770655" - } - }, - "9be9074028da42d39d044a78393a861f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "9d45b9a5de3e4cba9ac35ad2cb187f51": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "a14bc1c2130842568a5fde6698731e5f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "a3a3ef6d6337403cabea8b23f7c3021b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d125995cc0934239a01ba01b78529f21", - "placeholder": "​", - "style": "IPY_MODEL_634ae4c6cfe04673b1cdc9c9cac4cbf9", - "value": "tokenizer.json: 100%" - } - }, - "ac5eacaaee8346c080e54ea7a52648a4": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HBoxModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_7981edf408d54d41bbeac42da7492c6b", - "IPY_MODEL_2b848e5a85bc42bc87945fd9ed5db038", - "IPY_MODEL_e88c33f37d6849e0b1a6b41254104cb9" - ], - "layout": "IPY_MODEL_33843107b93647b28985bfc37ea781ca" - } - }, - "ae7e90a811f94e75997d6a9ed1be8596": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "ba68b274c50b44ec9e02642378d271a6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_68a32b398e1c490393e01befdc260785", - "max": 51760, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_04cc963133d242779572d2e847fa3d65", - "value": 51760 - } - }, - "bb9f3379310d4b04be694996f3137b28": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "c2ea0a3f01f34ffa8c94ab9b5098e9da": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_d7f92e8332374313bee87ccd427446a4", - "max": 9085657, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_36799fbcd90d43128620ff98225a825d", - "value": 9085657 - } - }, - "c97c40c2bf2a41a8ae1c75e0a9c8ebff": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "ce9fcc5eff1f460d80b703a4ca32dad1": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "d032fe2ba5d647d99026fdade758c0cd": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "d125995cc0934239a01ba01b78529f21": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "d4b3770433bc41818372b7aed243fb31": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "d4bd5559d4134d64a943d57972c6ef39": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "d7375f0f048841b29a20601c122666e8": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_331f516c7a76456d801bc2a2feb228aa", - "placeholder": "​", - "style": "IPY_MODEL_9be9074028da42d39d044a78393a861f", - "value": "special_tokens_map.json: 100%" - } - }, - "d7f92e8332374313bee87ccd427446a4": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "da8ffc70820a48f5a12c6d4b5967015b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8ea52b105a7e44978caca33c0e7e815b", - "placeholder": "​", - "style": "IPY_MODEL_3662f1445ef34a50b462e601ed31bb69", - "value": " 345/345 [00:00<00:00, 23.9kB/s]" - } - }, - "e3c3bd9c4c124b0a8c88c83c1fc747d3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "e6533d3c91fd4359bc84ffd8e59af5a3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_88fcd51819b5483c9ab22df7ef89ab64", - "placeholder": "​", - "style": "IPY_MODEL_e6ffac074f1b476ba2ade11b37732af3", - "value": " 11.6k/11.6k [00:00<00:00, 81.5kB/s]" - } - }, - "e6ffac074f1b476ba2ade11b37732af3": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "e887160635cb4803b9f33845df615ec6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "e88c33f37d6849e0b1a6b41254104cb9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_89934c4f26834f15b9889ec36fee3b65", - "placeholder": "​", - "style": "IPY_MODEL_e887160635cb4803b9f33845df615ec6", - "value": " 230/230 [00:00<00:00, 11.6kB/s]" - } - }, - "e93d063faf984cc4aa51462418d9b57e": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "e99423a1ed3f4f72886b39368468b7c1": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "e9971d220fe24552a1e9aa299765cfb9": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "DescriptionStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "ea55293415ca48a4be97c2e1e4769122": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "ProgressStyleModel", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "ecdeaab4f8c94d6dade63bb06857c969": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_e93d063faf984cc4aa51462418d9b57e", - "max": 51760, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_9d45b9a5de3e4cba9ac35ad2cb187f51", - "value": 51760 - } - }, - "ece66fa2f128456fa2a82b8a28d1211c": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "f433ced9bfcd4a57ba691d3c1caeed08": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_51cd9026b1664819a67712996ca97bd5", - "max": 345, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_ea55293415ca48a4be97c2e1e4769122", - "value": 345 - } - }, - "f4519637bb43400a80ce83505101e8a5": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "f84bfc5390054ec687c157c4d68199a6": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "FloatProgressModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "danger", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_2be29a4553ad4dfea8a9bc620c81a3ae", - "max": 5702746390, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_94cbb87829d1486899e2ff6325c2ecdf", - "value": 5702745847 - } - }, - "f84d2fe4f1c24a34948755abf1f32b7f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_94730f13e92a4c9aac35c2cfb21fc48c", - "placeholder": "​", - "style": "IPY_MODEL_620c0de28ec74f71a021a2be96dccf3a", - "value": " 51760/51760 [00:01<00:00, 52026.13 examples/s]" - } - }, - "f878c2e00bc240c7b0333cce950080e1": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "f899a815142542219bde22ff792fb60c": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "1.5.0", - "model_name": "HTMLModel", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4e7cb8e988114ed4b6fe09ff9f682dff", - "placeholder": "​", - "style": "IPY_MODEL_a14bc1c2130842568a5fde6698731e5f", - "value": " 44.3M/44.3M [00:00<00:00, 87.2MB/s]" - } - }, - "f9b01aebcbdc48a585b7942b0ee60a2d": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "fbae6e599d1644f39e5d86efa0f9f997": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "1.2.0", - "model_name": "LayoutModel", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" } - } - } - }, - "nbformat": 4, - "nbformat_minor": 0 + }, + "nbformat": 4, + "nbformat_minor": 0 }