Trending repositories for topic llama
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and ...
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transfor...
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any...
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
All-in-one AI CLI tool that integrates 20+ AI platforms, including OpenAI, Azure-OpenAI, Gemini, Claude, Mistral, Cohere, VertexAI, Bedrock, Ollama, Ernie, Qianwen, Deepseek...
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
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
Firefly: 大模型训练工具，支持训练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
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
A low-latency & high-throughput serving engine for LLMs
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
Welcome to the LLMs Interview Prep Guide! This GitHub repository offers a curated set of interview questions and answers tailored for Data Scientists. Enhance your understanding of Large Language Mode...
QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and ...
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transfor...
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any...
All-in-one AI CLI tool that integrates 20+ AI platforms, including OpenAI, Azure-OpenAI, Gemini, Claude, Mistral, Cohere, VertexAI, Bedrock, Ollama, Ernie, Qianwen, Deepseek...
ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
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
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
Firefly: 大模型训练工具，支持训练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
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
A low-latency & high-throughput serving engine for LLMs
Turn natual language into commands. Your CLI tasks, now as easy as a conversation. Run it 100% offline, or use OpenAI's models.
QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
End to End Generative AI Industry Projects on LLM Models with Deployment
Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.
Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, LLMs, RAGs, LangChain, Fine-tuning & AI Agents (CrewAI)
Welcome to the LLMs Interview Prep Guide! This GitHub repository offers a curated set of interview questions and answers tailored for Data Scientists. Enhance your understanding of Large Language Mode...
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
VSCode coding companion for software teams 🦆 Turn your team insights into a portable plug-and-play context for code generation. Alternative to GitHub Copilot & OpenAI GPT powered by OSS LLMs (Phi 3, ...
Yet another operator for running large language models on Kubernetes with ease. Powered by Ollama! 🐫
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
A high-throughput and memory-efficient inference and serving engine for LLMs
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and ...
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transfor...
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any...
ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
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
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.
A low-latency & high-throughput serving engine for LLMs
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
MinimalChat is a lightweight, open-source chat application that allows you to interact with various large language models.
End to End Generative AI Industry Projects on LLM Models with Deployment
QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.
CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.
Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, LLMs, RAGs, LangChain, Fine-tuning & AI Agents (CrewAI)
This is the official PyTorch implementation of "LLM-QBench: A Benchmark Towards the Best Practice for Post-training Quantization of Large Language Models", and also an efficient LLM compression tool w...
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
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
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)
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
Lightweight inference library for ONNX files, written in C++. It can run SDXL on a RPI Zero 2 but also Mistral 7B on desktops and servers.
Drop-in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM, ONNX). Powers 👋 Jan
A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and ...
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transfor...
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
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
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)
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.
Firefly: 大模型训练工具，支持训练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
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any...
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
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
llama and other large language models on iOS and MacOS offline using GGML library.
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
Lightweight inference library for ONNX files, written in C++. It can run SDXL on a RPI Zero 2 but also Mistral 7B on desktops and servers.
Grounded Multimodal Large Language Model with Localized Visual Tokenization
Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a...
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
Instant, controllable, local pre-trained AI models in Rust