3e4c5a323c* Fast inference repatch * Update llama.py * Update utils.py * Update utils.py * Update utils.py * Update mistral.py * Update __init__.py * Fix inference * Update mistral.py * fast lm_head * Remove fast path * Update rope_embedding.py * Update loader.py * LlamaAttention_fast_forward_inference * if past_key_value is not None and q_len == 1: * revert inference * Update loader.py * past_key_value * Update llama.py * Update llama.py * Fix SDPA * Update llama.py * padding * Inference * Update llama.py * Revert * Update mistral.py * faster inference * inference * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * inference * Update llama.py * Update utils.py * faster inference * Update llama.py * revert * lm_head * Update llama.py * inference * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update mistral.py * Update llama.py * faster inference * Update llama.py * fast inference * Update llama.py * Update llama.py * Update mistral.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * torch compile * past_key_values * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update utils.py * Update utils.py * Update utils.py * Update utils.py * Update llama.py * fast inference + saving config.json * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update mistral.py * fast inference again * more temp matrices * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * fast inference * Update mistral.py * Update llama.py * SDPA * attention_mask * New version * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update utils.py * Update utils.py * Update save.py * Update save.py * Torch 2.2.0 * Update save.py * mistral swa * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Fix SWA inference * Fix llm_int8_skip_modules * SWA inference * Update save.py * Update save.py * Update pyproject.toml * __version__ * __version__ * Update save.py * Update save.py * Update mistral.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Chat Templates * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * patch tokenizer * Update chat_templates.py * Saving, LlamaRotaryEmbedding issues * Update llama.py * Update mistral.py * Update mapper.py * Fix RoPE precision issues * Bugs * saving bugs * Update llama.py * readme * spaces * spaces * globals * slash * slashes * spaces * apache * Update save.py * Update save.py * Update loader.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * trainer * Update save.py * Update pyproject.toml * install * Update save.py * Update save.py * Update save.py * Update save.py * PeftModel token + saving * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * linking * llama.cpp bugs * Update save.py * Update save.py * saving * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update __init__.py * Update save.py * Update save.py * Update save.py * save * trainer * spaces * original
200 lines
5.9 KiB
TOML
200 lines
5.9 KiB
TOML
[build-system]
|
|
requires = ["setuptools", "setuptools-scm"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "unsloth"
|
|
dynamic = ["version"]
|
|
description = "2-5X faster LLM finetuning"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
license = {file = "LICENSE"}
|
|
keywords = ["ai", "llm",]
|
|
authors = [
|
|
{email = "info@unsloth.ai"},
|
|
{name = "Unsloth AI team"},
|
|
]
|
|
maintainers = [
|
|
{name = "Daniel Han", email = "danielhanchen@gmail.com"},
|
|
{name = "Michael Han", email = "info@unsloth.ai"},
|
|
]
|
|
classifiers = [
|
|
"Programming Language :: Python",
|
|
]
|
|
|
|
[tool.setuptools.dynamic]
|
|
version = {attr = "unsloth.models._utils.__version__"}
|
|
|
|
[tool.setuptools]
|
|
include-package-data = false
|
|
|
|
[tool.setuptools.packages.find]
|
|
exclude = ["images*"]
|
|
|
|
[project.optional-dependencies]
|
|
huggingface = [
|
|
"transformers>=4.37.0",
|
|
"datasets",
|
|
"sentencepiece",
|
|
"accelerate>=0.26.1",
|
|
"trl>=0.7.9",
|
|
"peft>=0.7.1",
|
|
"tqdm",
|
|
"psutil",
|
|
"wheel>=0.42.0",
|
|
"numpy",
|
|
]
|
|
cu118only = [
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu121only = [
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu118onlytorch211 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu121onlytorch211 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu118onlytorch220 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu121onlytorch220 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu118 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118only]",
|
|
]
|
|
cu121 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121only]",
|
|
]
|
|
cu118-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch211]",
|
|
]
|
|
cu121-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch211]",
|
|
]
|
|
cu118-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch220]",
|
|
]
|
|
cu121-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch220]",
|
|
]
|
|
kaggle = [
|
|
"unsloth[huggingface]",
|
|
]
|
|
conda = [
|
|
"unsloth[huggingface]",
|
|
]
|
|
colab = [
|
|
"unsloth[cu121]",
|
|
]
|
|
colab-ampere = [
|
|
"unsloth[cu121]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
colab-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch211]",
|
|
]
|
|
colab-ampere-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch211]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
colab-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch220]",
|
|
]
|
|
colab-ampere-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch220]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu118-ampere = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118only]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu121-ampere = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121only]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu118-ampere-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch211]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu121-ampere-torch211 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch211]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu118-ampere-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch220]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu121-ampere-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch220]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
|
|
[project.urls]
|
|
homepage = "http://www.unsloth.ai"
|
|
documentation = "https://github.com/unslothai/unsloth"
|
|
repository = "https://github.com/unslothai/unsloth"
|