Awesome Open Source

Programming Languages

Search results for python llm

867 search results found

Languagemodels ⭐ 1,127

Explore large language models on any computer with 512MB of RAM

Safe Rlhf ⭐ 1,040

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Bert4torch ⭐ 1,035

An elegent pytorch implement of transformers

Gorilla Cli ⭐ 997

LLMs for your CLI

Data Juicer ⭐ 994

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！

Langroid ⭐ 988

Harness LLMs with Multi-Agent Programming

Ray Llm ⭐ 972

RayLLM - LLMs on Ray

Chameleon Llm ⭐ 957

Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".

An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM)

Shell Ai ⭐ 904

LangChain powered shell command generator and runner CLI

Skywork ⭐ 894

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，

Seagoat ⭐ 881

local-first semantic code search engine

Replitlm ⭐ 873

Inference code and configs for the ReplitLM model family

Spacy Llm ⭐ 806

🦙 Integrating LLMs into structured NLP pipelines

Curated Transformers ⭐ 790

🤖 A PyTorch library of curated Transformer models and their composable components

Autollm ⭐ 769

Ship RAG based LLM web apps in seconds.

Db Gpt Hub ⭐ 759

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

Chatgentitle ⭐ 738

🌟 ChatGenTitle：使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools.

Langcorn ⭐ 729

⛓️ Serving LangChain LLM apps automagically with FastApi. LLMops

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Llmcompiler ⭐ 714

LLMCompiler: An LLM Compiler for Parallel Function Calling

Llama 2 Open Source Llm Cpu Inference ⭐ 712

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

Llm Engine ⭐ 711

Scale LLM Engine public repository

Openrlhf ⭐ 704

A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone

Salesforce open-source LLMs with 8k sequence length.

Genossgpt ⭐ 670

One API for all LLMs either Private or Public (Anthropic, Llama V2, GPT 3.5/4, Vertex, GPT4ALL, HuggingFace ...) 🌈🐂 Replace OpenAI GPT with any LLMs in your app with one line.

Openllmetry ⭐ 664

Open-source observability for your LLM application, based on OpenTelemetry

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

Microagents ⭐ 659

Agents Capable of Self-Editing Their Prompts / Python Code

Llm Blender ⭐ 655

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

The all-in-one LLMOps platform: prompt management, evaluation, human feedback, and deployment all in one place.

A lightweight framework for building LLM-based agents

Lawyer Llama ⭐ 636

中文法律LLaMA (LLaMA for Chinese legel domain)

Aiconfig ⭐ 636

aiconfig -- config-driven, source control friendly AI application development

Openai Forward ⭐ 624

🚀 大语言模型高效转发服务 · An efficient forwarding service designed for LLMs. · OpenAI API Reverse Proxy

Serving multiple LoRA finetuned LLM as one

Rag Demystified ⭐ 610

An LLM-powered advanced RAG pipeline built from scratch

Ragxplorer ⭐ 603

Open-source tool to visualise your RAG documents 🔮

PhoGPT: Generative Pre-training for Vietnamese (2023)

Fastrag ⭐ 591

Efficient Retrieval Augmentation and Generation Framework

Tanuki.py ⭐ 579

Easily build LLM-powered apps that get cheaper and faster over time.

魔搭大模型训练推理部署工具箱，支持LLaMA、千问、ChatGLM、BaiChuan等多种模型及Lo LLM training/inference/deployment framework of ModelScope community, Support various models like LLaMA, Qwen, ChatGLM, Baichuan and others, and training methods like LoRA, ResTuning, NEFTune, etc.)

Llm Guard ⭐ 567

The Security Toolkit for LLM Interactions

Llmflows ⭐ 565

LLMFlows - Simple, Explicit and Transparent LLM Apps

Attention_sinks ⭐ 565

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

LLM vulnerability scanner

Agently ⭐ 558

[AI Agent Application Development Framework] - 🚀 Build AI agent native application in very few code 💬 Easy to interact with AI agent in code using structure data and chained-calls syntax 🧩 Enhance AI Agent using plugins instead of rebuild a whole new agent

Generative Ai Python ⭐ 553

The Google AI Python SDK enables developers to use Google's state-of-the-art generative AI models (like Gemini and PaLM) to build AI-powered features and applications.

SEAIT is a user-friendly application that simplifies the installation process of AI-related projects

Asreview ⭐ 525

Active learning for systematic reviews

Awesome Efficient Llm ⭐ 521

A curated list for Efficient Large Language Models

Maxtext ⭐ 520

A simple, performant and scalable Jax LLM!

Llama Moe ⭐ 497

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

Unified Reinforcement Learning Framework

Content Chatbot ⭐ 496

Build a chatbot or Q&A bot of your website's content

Squeezellm ⭐ 486

SqueezeLLM: Dense-and-Sparse Quantization

Aqueduct ⭐ 482

Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.

Mixtralkit ⭐ 481

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

Vectordb ⭐ 479

A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search.

Woodpecker ⭐ 473

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models. The first work to correct hallucinations in MLLMs.

Awesome Gpt Prompt Engineering ⭐ 466

A curated list of awesome resources, tools, and other shiny things for GPT prompt engineering.

Llama2 Code Interpreter ⭐ 464

Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

Omniquant ⭐ 464

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

official repository for ChatIE paper and a tool of IE using ChatGPT. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and the speed/model will be slow/overloaded.)

Generativeaiexamples ⭐ 458

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Lifereloaded ⭐ 458

A life simulation Game powered by GPT-4's “Advanced Data Analysis” function , offering you a second chance at life. 由GPT4的Advanced Data Analysis功能驱动的人生重来模拟器，给您人生第二春。

Opencopilot ⭐ 446

🕊️ Build and embed open-source AI Copilots into your product with ease

Openscene ⭐ 443

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

Incarnamind ⭐ 440

Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs

Phasellm ⭐ 426

Large language model evaluation and workflow framework from Phase AI.

LLMs and Machine Learning done easily

Finetune_llms ⭐ 421

Repo for fine-tuning Casual LLMs

Gpt Cli ⭐ 417

Command-line interface for ChatGPT, Claude and Bard

Chatdocs ⭐ 402

Chat with your documents offline using AI.

irresponsible innovation. Try now at https://chat.dev/

Codefuse Modelcache ⭐ 392

A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.

PULSE: Pretrained and Unified Language Service Engine

Clarifai Python ⭐ 384

Experience the power of Clarifai’s AI platform with the python SDK. 🌟 Star to support our work!

Exact structure out of any language model completion.

Aquila2 ⭐ 376

The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.

Qizhengpt ⭐ 376

QiZhenGPT: An Open Source Chinese Medical Large Language Model｜一个开源的中文医疗大语言模型

Chainfury ⭐ 368

🦋 Production grade chaining engine behind TuneChat. Self host today!

Insight ⭐ 366

INSIGHT is an autonomous AI that can do medical research!

Reflexion Draft ⭐ 365

Reflexion: an autonomous agent with dynamic memory and self-reflection

Can Ai Code ⭐ 364

Self-evaluating interview for AI coders

Llm Strategy ⭐ 360

Directly Connecting Python to LLMs - Dataclasses & Interfaces <-> LLMs

Agentchain ⭐ 355

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks

Huixiangdou ⭐ 351

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Llm Shearing ⭐ 351

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

A fast and minimal framework for building agent-integrated systems

Devlooper ⭐ 347

A program synthesis agent that autonomously fixes its output by running tests!

Promptmap ⭐ 346

automatically tests prompt injection attacks on ChatGPT instances

Instruct Eval ⭐ 346

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

Infinity ⭐ 341

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of sentence-transformer models and frameworks.

Obsidian Copilot ⭐ 341

🤖 A prototype assistant for writing and thinking

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

Docker Llama2 Chat ⭐ 333

Play LLaMA2 (official / 中文版 / INT4 / llama2.cpp) Together! ONLY 3 STEPS! ( non GPU / 5GB vRAM / 8~14GB vRAM)

Related Searches

Python Deep Learning (22,937)

Python Machine Learning (20,195)

Python Dataset (14,792)

Python Tensorflow (13,736)

Python Command Line (13,351)

Python Jupyter Notebook (12,976)

Python Html (10,924)

Python Database (10,397)

Python Natural Language Processing (9,064)

Python Artificial Intelligence (8,580)

101-200 of 867 search results

Privacy | About | Terms | Follow Us On Twitter

Copyright 2018-2024 Awesome Open Source. All rights reserved.