[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

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

A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Use `llama2-wrapper` as your local llama2 backend for Generative Agents/Apps.

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)

improve Llama-2's proficiency in comprehension, generation, and translation of Chinese.

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

Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.

Examples of RAG using Llamaindex with local LLMs - Gemma, Mixtral 8x7B, Llama 2, Mistral 7B, Orca 2, Phi-2, Neural 7B

InsightSolver: Colab notebooks for exploring and solving operational issues using deep learning, machine learning, and related models.

LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces

📚 Local PDF-Integrated Chat Bot: Secure Conversations and Document Assistance with LLM-Powered Privacy

[KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model

Examples of RAG using LangChain with local LLMs - Mixtral 8x7B, Llama 2, Mistral 7B, Orca 2, Phi-2, Neural 7B

Chat to LLaMa 2 that also provides responses with reference documents over vector database. Locally available model using GPTQ 4bit quantization.

Introducing Project Zephyrine: Elevating Your Interaction Plug and Play, and Employing GPU Acceleration within a Modernized Automata Local Graphical User Interface.