🦜🔗 Build context-aware reasoning applications

A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically Ch…

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Instruct-tune LLaMA on consumer hardware

LLM inference in C/C++

Llama 3 ORPO Fine Tuning on A100 in Colab Pro.

Finetune LLaMA-7B with Chinese instruction datasets

llama3-lora微调

LlaMA3-SFT, Meta-Llama-3-8B/Meta-Llama-3-8B-Instruct微调(transformers)/LORA(peft)/推理, 支持中文(chinese, zh)

对llama3进行全参微调、lora微调以及qlora微调。

中文法律LLaMA (LLaMA for Chinese legel domain)

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

Quick tutorial showing how to fine-tune Llama3.1 with nothing but free tools and text data. All code included in ipynb. For a step by step walkthrough take a look at the tutorial below on medium.

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

CamelBell（驼铃) is be a Chinese Language Tuning project based on LoRA. CamelBell is belongs to Project Luotuo(骆驼), an open sourced Chinese-LLM project created by 冷子昂 @ 商汤科技 & 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技

The official Meta Llama 3 GitHub site

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Patch-based Convlutional Encoder for vibrational spectrum recognition

MetDIT: Transforming and Analyzing Clinical Metabolomics Data with Convolutional Neural Networks