From c931ec40c6dd9d7cb9578be8f53ca079ca668d28 Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Fri, 15 Dec 2023 12:57:08 +1100 Subject: [PATCH] Fix packaging, readme --- README.md | 7 ++++--- pyproject.toml | 4 ++++ 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 45f235f6c7..422abcf3b8 100644 --- a/README.md +++ b/README.md @@ -6,9 +6,10 @@ ## 2-5x faster 60% less memory local QLoRA finetuning * Supports Llama 7b, 13b, 70b, CodeLlama 34b, Mistral 7b, TinyLlama and all Llama archs! -* Mistral 7b [(Colab example)](https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing) on 1 A100 2.2x faster, uses 62% less VRAM (12.4GB). -* CodeLlama 34b [(Colab example)](https://colab.research.google.com/drive/1gdHyAx8XJsz2yNV-DHvbHjR1iCef5Qmh?usp=sharing) does not OOM is 1.9x faster, uses 32% less VRAM (27GB). -* Kaggle 2 Tesla T4s 5.28x faster on Alpaca. [(Kaggle example)](https://www.kaggle.com/danielhanchen/unsloth-laion-t4-ddp) +* Llama 7b [Colab T4 example](https://colab.research.google.com/drive/1n-fgduZhRUsSjgpqNtVkXA3rSfE7iBdg?usp=sharing) on 1 T4 2x faster, uses 43% less VRAM (8.4GB) LAION dataset. [Alpaca T4 example](https://colab.research.google.com/drive/1oW55fBmwzCOrBVX66RcpptL3a99qWBxb?usp=sharing) 2x faster on 1 T4, using 6.4GB VRAM. +* Mistral 7b [Colab A100 example](https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing) on 1 A100 2.2x faster, uses 62% less VRAM (12.4GB). +* CodeLlama 34b [Colab example](https://colab.research.google.com/drive/1gdHyAx8XJsz2yNV-DHvbHjR1iCef5Qmh?usp=sharing) does not OOM is 1.9x faster, uses 32% less VRAM (27GB). +* Kaggle 2 Tesla T4s 5.28x faster on Alpaca. [Kaggle example](https://www.kaggle.com/danielhanchen/unsloth-laion-t4-ddp) * All kernels written in [OpenAI's Triton](https://openai.com/research/triton) language. * 0% loss in accuracy - no approximation methods - all exact. * No change of hardware necessary. Supports NVIDIA GPUs since 2018+. Minimum CUDA Compute Capability 7.0 (V100, T4, Titan V, RTX 20, 30, 40x, A100, H100, L40 etc) [Check your GPU](https://developer.nvidia.com/cuda-gpus) diff --git a/pyproject.toml b/pyproject.toml index 3520b7dd93..44abff8e61 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -39,6 +39,7 @@ huggingface = [ "accelerate", "trl", "peft", + "packaging", ] cu118only = [ "xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'", @@ -70,16 +71,19 @@ cu118_ampere = [ "unsloth[huggingface]", "bitsandbytes", "unsloth[cu118only]", + "ninja", "flash-attn", ] cu121_ampere = [ "unsloth[huggingface]", "bitsandbytes", "unsloth[cu121only]", + "ninja", "flash-attn", ] colab_ampere = [ "unsloth[cu118]", + "ninja", "flash-attn", ]