Use PEFT or Full-parameter to finetune 350+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)
agent
deploy
dpo
internvl
liger
llama
llama3
llava
llm
lora
megatron
minicpm-v
modelscope
multimodal
peft
pre-training
qwen2
qwen2-vl
reflection
sft
Updated 2024-10-15 17:23:20 +08:00