Use PEFT or Full-parameter to finetune 350+ LLMs or 90+ MLLMs. (Qwen2.5, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
agent
reflection
deploy
llama
lora
liger
peft
multimodal
sft
megatron
dpo
pre-training
llm
modelscope
llava
qwen2
llama3
minicpm-v
internvl
qwen2-vl
-
Updated
Sep 24, 2024 - Python