Files
axolotl/requirements.txt
NanoCode012 a098df527b feat: add Mistral Small 4 (#3502)
* feat: add mistral small 4

* fix: update mistral common

* fix: deepcopy when passing in tokenizer

* feat: add doc on reasoning and thinking section

* fix: don't use custom tokenizer and quantize experts

* chore: update docs and configs

* chore: update doc to follow official name

* feat: update cce to include mistral4

* chore: move

* fix: naming

* fix: test mock breaking get_text_config check

* fix: enable CCE and add expert block targetting to configs

* chore: docs

* fix: use act checkpointing

* chore: doc

* chore: docs

* chore: docs
2026-03-17 09:39:05 +07:00

79 lines
1.2 KiB
Plaintext

--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
# START section of dependencies that don't install on Darwin/MacOS
bitsandbytes==0.49.1
triton>=3.4.0
mamba-ssm==1.2.0.post1
xformers>=0.0.23.post1
liger-kernel==0.7.0
# END section
packaging==26.0
huggingface_hub>=1.1.7
peft>=0.18.1
tokenizers>=0.22.1
transformers==5.3.0
accelerate==1.13.0
datasets==4.5.0
deepspeed>=0.18.6,<0.19.0
trl==0.29.0
hf_xet==1.3.2
kernels==0.12.2
fla-core==0.4.1
flash-linear-attention==0.4.1
trackio>=0.16.1
typing-extensions>=4.15.0
optimum==1.16.2
hf_transfer
sentencepiece
gradio>=6.2.0,<7.0
modal==1.3.0.post1
pydantic>=2.10.6
addict
fire
PyYAML>=6.0
requests
wandb
einops
colorama
numba>=0.61.2
numpy>=2.2.6
# qlora things
evaluate==0.4.1
scipy
nvidia-ml-py==12.560.30
art
tensorboard
python-dotenv==1.0.1
# remote filesystems
s3fs>=2024.5.0
gcsfs>=2025.3.0
adlfs>=2024.5.0
ocifs==1.3.2
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==0.16.0
openenv-core==0.1.0
schedulefree==1.4.1
axolotl-contribs-lgpl==0.0.7
axolotl-contribs-mit==0.0.6
# telemetry
posthog==6.7.11
mistral-common==1.10.0