Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥

Efficient Triton Kernels for LLM Training

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Interact with your SQL database, Natural Language to SQL using LLMs

A PyTorch Library for Meta-learning Research

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

Easiest and laziest way for building multi-agent LLMs applications.

🎯 Task-oriented embedding tuning for BERT, CLIP, etc.

制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Webui for using XTTS and for finetuning it

Finetuning large language models for GDScript generation.

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

[ACL 2024] Official resources of "ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models".

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.

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

从词表到微调这就是你所需的一切

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

🔥 Korean GPT-2, KoGPT2 FineTuning cased. 한국어 가사 데이터 학습 🔥

llama2 finetuning with deepspeed and lora