8bbad21bfd
* llama4 support * add xet support [skip ci] * be flexible on transformers version and skip test on version * don't use deepspeed for the fix_untrained_tokens test * reordering to trigger torch 2.6.0 tests first * slightly smaller train set * use 4.51.0 for now * remove stray print, add llama4 chat template to schema, bump peft to 0.15.1 * patches to make llama4 performant * add preliminary fp8 support
68 lines
1006 B
Plaintext
68 lines
1006 B
Plaintext
--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
|
|
|
|
# START section of dependencies that don't install on Darwin/MacOS
|
|
bitsandbytes==0.45.4
|
|
triton>=3.0.0
|
|
mamba-ssm==1.2.0.post1
|
|
xformers>=0.0.23.post1
|
|
autoawq==0.2.7.post3
|
|
liger-kernel==0.5.6
|
|
# END section
|
|
|
|
packaging==23.2
|
|
|
|
peft==0.15.1
|
|
transformers==4.51.0
|
|
tokenizers>=0.21.1
|
|
accelerate==1.6.0
|
|
datasets==3.5.0
|
|
deepspeed>=0.15.4
|
|
trl==0.16.1
|
|
hf_xet==1.0.0
|
|
|
|
optimum==1.16.2
|
|
hf_transfer
|
|
sentencepiece
|
|
gradio==5.23.3
|
|
|
|
modal==0.70.5
|
|
pydantic==2.10.6
|
|
addict
|
|
fire
|
|
PyYAML>=6.0
|
|
requests
|
|
wandb
|
|
einops
|
|
colorama
|
|
numba
|
|
numpy>=1.24.4,<=2.0.1
|
|
|
|
# qlora things
|
|
evaluate==0.4.1
|
|
scipy
|
|
scikit-learn==1.4.2
|
|
nvidia-ml-py==12.560.30
|
|
art
|
|
tensorboard
|
|
python-dotenv==1.0.1
|
|
|
|
# remote filesystems
|
|
s3fs>=2024.5.0
|
|
gcsfs>=2024.5.0
|
|
# adlfs
|
|
|
|
zstandard==0.22.0
|
|
fastcore
|
|
|
|
# lm eval harness
|
|
lm_eval==0.4.7
|
|
langdetect==1.0.9
|
|
immutabledict==4.2.0
|
|
antlr4-python3-runtime==4.13.2
|
|
|
|
torchao==0.9.0
|
|
schedulefree==1.4.1
|
|
|
|
axolotl-contribs-lgpl==0.0.6
|
|
axolotl-contribs-mit==0.0.3
|