Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

AirLLM 70B inference with single 4GB GPU

Accessible large language models via k-bit quantization for PyTorch.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴

chatglm 6b finetuning and alpaca finetuning

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

🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

🌿孙思邈中文医疗大模型(Sunsimiao)：提供安全、可靠、普惠的中文医疗大模型

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

对llama3进行全参微调、lora微调以及qlora微调。

Enhancing LLMs with LoRA

LongQLoRA: Extent Context Length of LLMs Efficiently

qwen models finetuning

Large language Model fintuning bloom , opt , gpt, gpt2 ,llama,llama-2,cpmant and so on

Fine-Tuning Falcon-7B, LLAMA 2 with QLoRA to create an advanced AI model with a profound understanding of the Indian legal context.

使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE

VerifAI initiative to build open-source easy-to-deploy generative question-answering engine that can reference and verify answers for correctness (using posteriori model)

Use QLoRA to tune LLM in PyTorch-Lightning w/ Huggingface + MLflow

vision language models finetuning notebooks & use cases (Medgemma - paligemma - florence .....)

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

Implements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the LLaMA2 model to follow human instructions, similar to InstructGPT or ChatGPT, but on a much smaller scale.

Finetune any model on HF in less than 30 seconds

Open-source framework for turning expert knowledge into PII-free synthetic conversational data and production-ready LoRA adapters.