42076f6580* Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * revert * revert * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update cross_entropy_loss.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * rope * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * llama * Update llama.py * gemma * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update save.py * RoPE * Update llama.py * Update llama.py * Update llama.py * Update gemma.py * correct_dtype * Update gemma.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Chat Templates * Update README.md * Update README.md * Update llama.py * DoRA * Update _utils.py * Update chat_templates.py * Update llama.py * Hotfix - fix DoRA, Gemma prompt template (#202) (#203) * 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 * Gemma * Update pyproject.toml * Update mapper.py * Update fast_lora.py * FastGemmaModel * model_type * Update llama.py * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update llama.py * Update fast_lora.py * Update llama.py * Update llama.py * Update cross_entropy_loss.py * Update llama.py * Update llama.py * gemma * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update fast_lora.py * Update fast_lora.py * Fast CE Loss * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * CE * Update llama.py * Update llama.py * Update cross_entropy_loss.py * Update geglu.py * Update cross_entropy_loss.py * revert * Update llama.py * Update llama.py * norm * Update gemma.py * Update gemma.py * position_ids * Update gemma.py * Update gemma.py * pos * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update cross_entropy_loss.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * revert * revert * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update cross_entropy_loss.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * rope * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * llama * Update llama.py * gemma * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update save.py * RoPE * Update llama.py * Update llama.py * Update llama.py * Update gemma.py * correct_dtype * Update gemma.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Chat Templates * Update README.md * Update README.md * Update llama.py * DoRA * Update _utils.py * Update chat_templates.py * Update pyproject.toml * Small fixes * Update pyproject.toml * Approx gelu * Update geglu.py * Approx gelu * Update llama.py * Update __init__.py * Update __init__.py * Update _utils.py * Update geglu.py * Update gemma.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Update gemma.py * Fix Gemma merging * Update rms_layernorm.py * Update gemma.py * Update pyproject.toml * Layernorms * Gemma precision * Update gemma.py * sqrt * Update gemma.py * Update save.py * RoPE and Gemma precision * Update rms_layernorm.py * Fix warning * Update chat_templates.py * Update chat_templates.py * Update save.py * Update save.py * Update save.py * Update chat_templates.py * Update llama.py * model_name * Update loader.py * Tokenizer overwritten * Update llama.py * Update llama.py * Update llama.py * Update save.py * Accuracy * Revert * Update save.py * Update fast_lora.py * Update fast_lora.py * Update fast_lora.py * Update fast_lora.py * Update fast_lora.py * Update chat_templates.py * Update save.py * Update save.py * Update llama.py * Update llama.py * Account for DoRA * Update llama.py * Update save.py * GGUF incorrect * Update save.py * Update pyproject.toml * kaggle new * Update pyproject.toml * Update pyproject.toml * upcasting * Fix Colab * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml
239 lines
7.3 KiB
TOML
239 lines
7.3 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 = [
|
|
"tyro",
|
|
"transformers>=4.38.2",
|
|
"datasets>=2.16.0",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"psutil",
|
|
"wheel>=0.42.0",
|
|
"numpy",
|
|
"accelerate>=0.26.1",
|
|
"trl>=0.7.9",
|
|
"peft>=0.7.1",
|
|
]
|
|
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'",
|
|
]
|
|
cu118onlytorch212 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu121onlytorch212 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-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-torch212 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch212]",
|
|
]
|
|
cu121-torch212 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch212]",
|
|
]
|
|
cu118-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch220]",
|
|
]
|
|
cu121-torch220 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch220]",
|
|
]
|
|
kaggle = [
|
|
"unsloth[huggingface]",
|
|
]
|
|
kaggle-new = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
]
|
|
conda = [
|
|
"unsloth[huggingface]",
|
|
]
|
|
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",
|
|
]
|
|
colab-new = [
|
|
"tyro",
|
|
"transformers>=4.38.2",
|
|
"datasets>=2.16.0",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"psutil",
|
|
"wheel>=0.42.0",
|
|
"numpy",
|
|
]
|
|
colab-no-deps = [
|
|
"accelerate>=0.26.1",
|
|
"trl>=0.7.9",
|
|
"peft>=0.7.1",
|
|
"xformers",
|
|
"bitsandbytes",
|
|
]
|
|
colab-ampere = [
|
|
"unsloth[colab-ampere-torch220]",
|
|
"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"
|