From 6e4ebe4040e53e3c6873d0cc2a4a90e87218e27c Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Tue, 30 Apr 2024 05:59:02 +1000 Subject: [PATCH] Phi-3 (#397) * Fix prompt * Update chat_templates.py * fix_untrained_tokens * Update llama.py * add tokens * Update _utils.py * Update tokenizer_utils.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * pad_token * Update chat_templates.py * Update chat_templates.py * tokenizer * Update save.py * Update chat_templates.py * Update chat_templates.py * patch tokenizer padding * Update tokenizer_utils.py * Update save.py * Fix: loading models with resized vocabulary (#377) * new: vocab resize on load * new: gitignore * GGUF fix * Readme (#390) * Update README.md * Update README.md --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * Update README.md * Delete .gitignore * Phi-3 * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md --------- Co-authored-by: Igor Kilbas Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> --- README.md | 27 +++++++++++++++------------ unsloth/models/mapper.py | 4 ++++ 2 files changed, 19 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 6df6616225..07bcf2cf5f 100644 --- a/README.md +++ b/README.md @@ -20,23 +20,25 @@ All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. -| Unsloth supports | Free Notebooks | Performance | Memory use | -|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| -| **Llama 3 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2x faster | 60% less | -| **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 73% less | -| **Gemma (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 71% less | -| **Llama 3 (8B)** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-llama-3-8b-unsloth-notebook) | 5x faster\* | 73% less | -| **ORPO** | [▶️ Start on Colab](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less | -| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less | +| Unsloth supports | Free Notebooks | Performance | Memory use | +|-----------|---------|--------|----------| +| **Llama 3 (8B)** | [▶️ Start for free](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2x faster | 60% less | +| **Mistral (7B)** | [▶️ Start for free](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 73% less | +| **Gemma (7B)** | [▶️ Start for free](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 71% less | +| **ORPO** | [▶️ Start for free](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) | 1.9x faster | 43% less | +| **DPO Zephyr** | [▶️ Start for free](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 43% less | +| **Phi-3 (3.8B)** | [▶️ Start for free](https://colab.research.google.com/drive/1NvkBmkHfucGO3Ve9s1NKZvMNlw5p83ym?usp=sharing) | 2x faster | 50% less | +| **TinyLlama** | [▶️ Start for free](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less | - Benchmarking compared to FA2 + Hugging Face combined. -- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. -- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. -- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster. +- **Kaggle Notebooks** for [Llama-3 8b](https://www.kaggle.com/code/danielhanchen/kaggle-llama-3-8b-unsloth-notebook), [Gemma 7b](https://www.kaggle.com/code/danielhanchen/kaggle-gemma-7b-unsloth-notebook/), [Mistral 7b](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) +- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for Llama-3. And ChatML for [Mistral 7b](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing). +- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for continued pretraining / raw text. ## 🦥 Unsloth.ai News - 📣 NEW! [Llama-3 8b](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) now works! Llama-3 70b also works (change the model name in the notebook). - 📣 NEW! [ORPO support](https://colab.research.google.com/drive/11t4njE3c4Lxl-07OD8lJSMKkfyJml3Tn?usp=sharing) is here! +- 📣 NEW! [Phi-3 3.8b support](https://colab.research.google.com/drive/1NvkBmkHfucGO3Ve9s1NKZvMNlw5p83ym?usp=sharing) is here! - 📣 NEW! We cut memory usage by a [further 30%](https://unsloth.ai/blog/long-context) and now support fine-tuning of LLMs with [4x longer context windows](https://unsloth.ai/blog/long-context)! No change required if you're using our notebooks. To enable, simply change 1 line: ```python model = FastLanguageModel.get_peft_model( @@ -45,7 +47,7 @@ model = FastLanguageModel.get_peft_model( ) ``` - 📣 [CodeGemma](https://colab.research.google.com/drive/19lwcRk_ZQ_ZtX-qzFP3qZBBHZNcMD1hh?usp=sharing) now works along with [Gemma 7b](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) and [Gemma 2b](https://colab.research.google.com/drive/15gGm7x_jTm017_Ic8e317tdIpDG53Mtu?usp=sharing) -- 📣 [2x faster inference](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) added for all our models +- 📣 [2x faster inference](https://colab.research.google.com/drive/1aqlNQi7MMJbynFDyOQteD2t0yVfjb9Zh?usp=sharing) added for all our models ## 🔗 Links and Resources | Type | Links | @@ -190,6 +192,7 @@ fourbit_models = [ "unsloth/gemma-2b-bnb-4bit", "unsloth/gemma-2b-it-bnb-4bit", # Instruct version of Gemma 2b "unsloth/llama-3-8b-bnb-4bit", # [NEW] 15 Trillion token Llama-3 + "unsloth/Phi-3-mini-4k-instruct-bnb-4bit", ] # More models at https://huggingface.co/unsloth model, tokenizer = FastLanguageModel.from_pretrained( diff --git a/unsloth/models/mapper.py b/unsloth/models/mapper.py index 769cbff536..b4fbe57387 100644 --- a/unsloth/models/mapper.py +++ b/unsloth/models/mapper.py @@ -140,6 +140,10 @@ __INT_TO_FLOAT_MAPPER = \ "unsloth/llama-3-70b-Instruct-bnb-4bit" : ( "meta-llama/Meta-Llama-3-70B-Instruct", ), + "unsloth/Phi-3-mini-4k-instruct-bnb-4bit" : ( + "unsloth/Phi-3-mini-4k-instruct", + "microsoft/Phi-3-mini-4k-instruct", + ), } INT_TO_FLOAT_MAPPER = {}