Skip to content
TechIndexSubmit
Back to directory

lmms-finetune

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

Similar tools

  • FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)

    Dev Tools
  • Manage and run OpenAI fine-tuning jobs efficiently within a modular C++ toolkit for large language model infrastructure.

    Models
  • Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

    Models
  • A Discord Bot for chatting with LLaMA, Vicuna, Alpaca, MPT, or any other Large Language Model (LLM) supported by text-generation-webui or llama.cpp.

    Models
  • LoRA / QLoRA fine-tuning of open-source models (DistilBERT, scales to Llama/Mistral) for transaction categorization — Colab notebook + training script

    Models
  • Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    Models