9b6ee83a73
* wip qlora + fsdp fixes
* more fixes
* make sure to load the lora 🤦
* only setup quantized meta on non-zero rank:
* only run setup_quantized_peft_meta_for_training for qlora+fsdp
* more fixes for qlora+fsdp
* chore: lint
* add example yml
* support mistral too
* fix for model_type and add mixtral support too
* set cpu_offload: false to reduce vram, constrain new accleerator logic to qlora + fsdp
* refactor for duplicate code
44 lines
583 B
Plaintext
44 lines
583 B
Plaintext
--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
|
|
packaging==23.2
|
|
peft==0.9.0
|
|
transformers==4.38.2
|
|
tokenizers==0.15.0
|
|
bitsandbytes>=0.43.0
|
|
accelerate==0.26.1
|
|
deepspeed==0.13.1
|
|
pydantic==2.6.3
|
|
addict
|
|
fire
|
|
PyYAML>=6.0
|
|
requests
|
|
datasets>=2.15.0
|
|
flash-attn==2.5.5
|
|
sentencepiece
|
|
wandb
|
|
einops
|
|
xformers==0.0.22
|
|
optimum==1.16.2
|
|
hf_transfer
|
|
colorama
|
|
numba
|
|
numpy>=1.24.4
|
|
# qlora things
|
|
evaluate==0.4.1
|
|
scipy
|
|
scikit-learn==1.2.2
|
|
pynvml
|
|
art
|
|
fschat==0.2.36
|
|
gradio==3.50.2
|
|
tensorboard
|
|
|
|
mamba-ssm==1.1.1
|
|
|
|
# remote filesystems
|
|
s3fs
|
|
gcsfs
|
|
# adlfs
|
|
|
|
trl>=0.7.9
|
|
fastcore>=1.5.29
|