cfafc707a1
* Update mapper.py * Update loader.py * Update llama.py * Update tokenizer_utils.py * info * edits * Create chat template * Fix tokenizer * Update tokenizer_utils.py * fix case where gguf saving fails due to first_conversion dtype (#630) * Support revision parameter in FastLanguageModel.from_pretrained (#629) * support `revision` parameter * match unsloth formatting of named parameters * clears any selected_adapters before calling internal_model.save_pretrained (#609) * Update __init__.py (#602) Check for incompatible modules before importing unsloth * Fixed unsloth/tokenizer_utils.py for chat training (#604) * Add GGML saving option to Unsloth for easier Ollama model creation and testing. (#345) * Add save to llama.cpp GGML to save.py. * Fix conversion command and path of convert to GGML function. * Add autosaving lora to the GGML function * Create lora save function for conversion to GGML * Test fix #2 for saving lora * Test fix #3 to save the lora adapters to convert to GGML * Remove unwated tokenizer saving for conversion to ggml and added a few print statements. * Needed tokenizer for saving, added it back, also made it more unslothy style by having positional arguments, and added a few messages. * Positional arguments didn't work out, so reverted to older version of the code, and added a few comments. * Test fix 1 for arch * Test fix 2 new Mistral error. * Test fix 3 * Revert to old version for testing. * Upload issue test fix 1 * Fix 2 uploading ggml * Positional ags added. * Temporray remove positional args * Fix upload again!!! * Add print statements and fix link * Make the calling name better * Create local saving for GGML * Add choosing directory to save local GGML. * Fix lil variable error in the save_to_custom_dir func * docs: Add LoraConfig parameters documentation (#619) * llama.cpp failing (#371) llama.cpp is failing to generate quantize versions for the trained models. Error: ```bash You might have to compile llama.cpp yourself, then run this again. You do not need to close this Python program. Run the following commands in a new terminal: You must run this in the same folder as you're saving your model. git clone https://github.com/ggerganov/llama.cpp cd llama.cpp && make clean && LLAMA_CUDA=1 make all -j Once that's done, redo the quantization. ``` But when i do clone this with recursive it works. Co-authored-by: Daniel Han <danielhanchen@gmail.com> * fix libcuda_dirs import for triton 3.0 (#227) * fix libcuda_dirs import for triton 3.0 * Update __init__.py * Update __init__.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update save.py * Update __init__.py * Update fast_lora.py * Update save.py * Update save.py * Update save.py * Update loader.py * Update save.py * Update save.py * quantize now llama-quantize * Update chat_templates.py * Update loader.py * Update mapper.py * Update __init__.py * embedding size * Update qwen2.py * docs * Update README.md * Update qwen2.py * README: Fix minor typo. (#559) * README: Fix minor typo. One-character typo fix while reading. * Update README.md --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update mistral.py * Update qwen2.py * Update qwen2.py * Update qwen2.py * Update llama.py * Update llama.py * Update llama.py * Update README.md * FastMistralModel * Update mistral.py * Update mistral.py * Update mistral.py * Update mistral.py * Update mistral.py * Auto check rope scaling * Update llama.py * Update llama.py * Update llama.py * GPU support * Typo * Update gemma.py * gpu * Multiple GGUF saving * Update save.py * Update save.py * check PEFT and base * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update chat_templates.py * Fix breaking bug in save.py with interpreting quantization_method as a string when saving to gguf (#651) * Nightly (#649) * Update llama.py * offload * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * continued pretraining trainer * Update trainer.py * Update trainer.py * Update trainer.py * Update trainer.py * is_bfloat16_supported * Update __init__.py * Update README.md * Update llama.py * is_bfloat16_supported * Update __init__.py * Mistral v3 * Phi 3 medium * Update chat_templates.py * Update chat_templates.py * Phi-3 * Update save.py * Update README.md Mistral v3 to Mistral v0.3 * Untrained tokens * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update llama.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update save.py * Update save.py * Update save.py * checkpoint * Update _utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update llama.py * accelerate * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * train_dataloader * Update llama.py * Update llama.py * Update llama.py * use_fast_convert * Update save.py * Update save.py * Update save.py * Update save.py * remove_special_tokens * Ollama * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update llama.py * Update chat_templates.py * Support bfloat16 GGUF * Update save.py * Update llama.py * fast_forward_inference * Update mapper.py * Update loader.py * Update llama.py * Update tokenizer_utils.py * info * edits * Create chat template * Fix tokenizer * Update tokenizer_utils.py * fix case where gguf saving fails due to first_conversion dtype (#630) * Support revision parameter in FastLanguageModel.from_pretrained (#629) * support `revision` parameter * match unsloth formatting of named parameters * clears any selected_adapters before calling internal_model.save_pretrained (#609) * Update __init__.py (#602) Check for incompatible modules before importing unsloth * Fixed unsloth/tokenizer_utils.py for chat training (#604) * Add GGML saving option to Unsloth for easier Ollama model creation and testing. (#345) * Add save to llama.cpp GGML to save.py. * Fix conversion command and path of convert to GGML function. * Add autosaving lora to the GGML function * Create lora save function for conversion to GGML * Test fix #2 for saving lora * Test fix #3 to save the lora adapters to convert to GGML * Remove unwated tokenizer saving for conversion to ggml and added a few print statements. * Needed tokenizer for saving, added it back, also made it more unslothy style by having positional arguments, and added a few messages. * Positional arguments didn't work out, so reverted to older version of the code, and added a few comments. * Test fix 1 for arch * Test fix 2 new Mistral error. * Test fix 3 * Revert to old version for testing. * Upload issue test fix 1 * Fix 2 uploading ggml * Positional ags added. * Temporray remove positional args * Fix upload again!!! * Add print statements and fix link * Make the calling name better * Create local saving for GGML * Add choosing directory to save local GGML. * Fix lil variable error in the save_to_custom_dir func * docs: Add LoraConfig parameters documentation (#619) * llama.cpp failing (#371) llama.cpp is failing to generate quantize versions for the trained models. Error: ```bash You might have to compile llama.cpp yourself, then run this again. You do not need to close this Python program. Run the following commands in a new terminal: You must run this in the same folder as you're saving your model. git clone https://github.com/ggerganov/llama.cpp cd llama.cpp && make clean && LLAMA_CUDA=1 make all -j Once that's done, redo the quantization. ``` But when i do clone this with recursive it works. Co-authored-by: Daniel Han <danielhanchen@gmail.com> * fix libcuda_dirs import for triton 3.0 (#227) * fix libcuda_dirs import for triton 3.0 * Update __init__.py * Update __init__.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update save.py * Update __init__.py * Update fast_lora.py * Update save.py * Update save.py * Update save.py * Update loader.py * Update save.py * Update save.py * quantize now llama-quantize * Update chat_templates.py * Update loader.py * Update mapper.py * Update __init__.py * embedding size * Update qwen2.py * docs * Update README.md * Update qwen2.py * README: Fix minor typo. (#559) * README: Fix minor typo. One-character typo fix while reading. * Update README.md --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update mistral.py * Update qwen2.py * Update qwen2.py * Update qwen2.py * Update llama.py * Update llama.py * Update llama.py * Update README.md * FastMistralModel * Update mistral.py * Update mistral.py * Update mistral.py * Update mistral.py * Update mistral.py * Auto check rope scaling * Update llama.py * Update llama.py * Update llama.py * GPU support * Typo * Update gemma.py * gpu * Multiple GGUF saving * Update save.py * Update save.py * check PEFT and base * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update chat_templates.py --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Eliot Hall <60240707+chrehall68@users.noreply.github.com> Co-authored-by: Rickard Edén <rickardeden@gmail.com> Co-authored-by: XiaoYang <xyangk@gmail.com> Co-authored-by: Oseltamivir <58582368+Oseltamivir@users.noreply.github.com> Co-authored-by: mahiatlinux <110882203+mahiatlinux@users.noreply.github.com> Co-authored-by: Sébastien De Greef <sebdg@binarycompany.com> Co-authored-by: Alberto Ferrer <albertof@barrahome.org> Co-authored-by: Thomas Viehmann <tv.github-private@beamnet.de> Co-authored-by: Walter Korman <lemurware@gmail.com> * Fix bug in save.py with interpreting quantization_method as a string that prevents GGUF from saving * Implemented better list management and then forgot to actually call the new list variable, fixed * Check type of given quantization method and return type error if not list or string * Update save.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Eliot Hall <60240707+chrehall68@users.noreply.github.com> Co-authored-by: Rickard Edén <rickardeden@gmail.com> Co-authored-by: XiaoYang <xyangk@gmail.com> Co-authored-by: Oseltamivir <58582368+Oseltamivir@users.noreply.github.com> Co-authored-by: mahiatlinux <110882203+mahiatlinux@users.noreply.github.com> Co-authored-by: Sébastien De Greef <sebdg@binarycompany.com> Co-authored-by: Alberto Ferrer <albertof@barrahome.org> Co-authored-by: Thomas Viehmann <tv.github-private@beamnet.de> Co-authored-by: Walter Korman <lemurware@gmail.com> * Revert "Fix breaking bug in save.py with interpreting quantization_method as …" (#652) This reverts commit 506cb68867296237e95bc53c32f1bfc9b1757960. * Revert "Revert "Fix breaking bug in save.py with interpreting quantization_me…" (#653) This reverts commit 2f48cc9af385579876fd45bd833169d1f1a2ea58. * Update llama.py * peft * patch * Update loader.py * retrain * 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 * offload * Update llama.py * Create a starter script for command-line training to integrate in ML ops pipelines. (#623) * Update chat_templates.py * Ollama * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Ollama * Update chat_templates.py * ollama * Update mapper.py * Update chat_templates.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update chat_templates.py * Update llama.py * Fixes * clearer messages * Update tokenizer_utils.py * Update tokenizer_utils.py * Update llama.py * Update llama.py * Update llama.py * log * Update __init__.py * Update llama.py * Update __init__.py * Create Merge.png * Create ollama.png * Gemma2 * Update llama.py * Update loader.py * Update pyproject.toml * Update pyproject.toml * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update _utils.py * Revert Gemma2 * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update rms_layernorm.py * Update gemma2.py * logit softcapping * Update cross_entropy_loss.py * Update llama.py * Update llama.py * Update gemma2.py * Update gemma2.py * Update cross_entropy_loss.py * Update llama.py * Update llama.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update llama.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update llama.py * Update gemma2.py * Update llama.py * Update llama.py * Update gemma2.py * Update gemma2.py * Update llama.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update gemma2.py * Update _utils.py * Update _utils.py * Update gemma2.py * compile flags * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update gemma2.py * Update gemma2.py * fixes * Update _utils.py * Fix generation * Update llama.py * Update llama.py * Update _utils.py * Update _utils.py * Update _utils.py * pad token * Update gemma2.py * pad token * Update _utils.py * Update llama.py * Update gemma2.py * edit warning * Update tokenizer_utils.py --------- Co-authored-by: Eliot Hall <60240707+chrehall68@users.noreply.github.com> Co-authored-by: Rickard Edén <rickardeden@gmail.com> Co-authored-by: XiaoYang <xyangk@gmail.com> Co-authored-by: Oseltamivir <58582368+Oseltamivir@users.noreply.github.com> Co-authored-by: mahiatlinux <110882203+mahiatlinux@users.noreply.github.com> Co-authored-by: Sébastien De Greef <sebdg@binarycompany.com> Co-authored-by: Alberto Ferrer <albertof@barrahome.org> Co-authored-by: Thomas Viehmann <tv.github-private@beamnet.de> Co-authored-by: Walter Korman <lemurware@gmail.com> Co-authored-by: ArcadaLabs-Jason <52756218+ArcadaLabs-Jason@users.noreply.github.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
282 lines
8.8 KiB
TOML
282 lines
8.8 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>=4.42.3",
|
|
"datasets>=2.16.0",
|
|
"sentencepiece>=0.2.0",
|
|
"tqdm",
|
|
"psutil",
|
|
"wheel>=0.42.0",
|
|
"numpy",
|
|
"accelerate>=0.26.1",
|
|
"trl>=0.7.9,<0.9.0",
|
|
"peft>=0.7.1,!=0.11.0",
|
|
"protobuf<4.0.0",
|
|
]
|
|
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'",
|
|
]
|
|
cu118onlytorch230 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.26.post1%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.26.post1%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.26.post1%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11'",
|
|
]
|
|
cu121onlytorch230 = [
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.26.post1-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.26.post1-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10'",
|
|
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.26.post1-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]",
|
|
]
|
|
cu118-torch230 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch230]",
|
|
]
|
|
cu121-torch230 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch230]",
|
|
]
|
|
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>=4.42.3",
|
|
"datasets>=2.16.0",
|
|
"sentencepiece>=0.2.0",
|
|
"tqdm",
|
|
"psutil",
|
|
"wheel>=0.42.0",
|
|
"numpy",
|
|
"protobuf<4.0.0",
|
|
]
|
|
colab-no-deps = [
|
|
"accelerate>=0.26.1",
|
|
"trl>=0.7.9",
|
|
"peft>=0.7.1",
|
|
"xformers",
|
|
"bitsandbytes",
|
|
"protobuf<4.0.0",
|
|
]
|
|
colab = [
|
|
"unsloth[cu121]",
|
|
]
|
|
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",
|
|
]
|
|
cu118-ampere-torch230 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu118onlytorch230]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
cu121-ampere-torch230 = [
|
|
"unsloth[huggingface]",
|
|
"bitsandbytes",
|
|
"unsloth[cu121onlytorch230]",
|
|
"packaging",
|
|
"ninja",
|
|
"flash-attn",
|
|
]
|
|
|
|
[project.urls]
|
|
homepage = "http://www.unsloth.ai"
|
|
documentation = "https://github.com/unslothai/unsloth"
|
|
repository = "https://github.com/unslothai/unsloth"
|