v0.1.0 release: Multi Task Fintuning Framework for Multiple base modles

Compare

Choose a tag to compare

chencyudel released this 27 Dec 08:20

· 78 commits to main since this release

This commit was created on GitHub.com and signed with GitHub’sverified signature. The key has expired.

GPG key ID:4AEE18F83AFDEB23

Expired

Verified

We released MFTCoder which supports finetuning Code Llama, Llama, Llama2, StarCoder, ChatGLM2, CodeGeeX2, Qwen, and GPT-NeoX models with LoRA/QLoRA.
mft_peft_hf is based on the HuggingFace Accelerate and deepspeed framework.
mft_atorch is based on theATorch frameworks, which is a fast distributed training framework of LLM.

Assets2

Movatterモバイル変換