Repository navigation

internvl

Website
Wikipedia

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

大语言模型 lora llama sft multimodal peft internvl liger deepseek-r1 embedding grpo open-r1 megatron llama4 qwen3 reranker moe

Python

10191

897

2 天前

InternLM / xtuner

A Next-Generation Training Engine Built for Ultra-Large MoE Models

大语言模型 agent deepseek-v3 gpt-oss internvl multimodal qwen3-moe reinforcement-learning

Python

4912

372

5 天前

NetEase-Media / grps_trtllm

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

大语言模型 openai tensorrt-llm chatglm llama3 qwen2 function-call ai-agent llama-index multi-modal deepseek-r1 phi qwq qwen2-vl minicpm-v internvl qwen3

Python

155

5 个月前