Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Code for Contrastive Preference Learning (CPL)

Put the MacOS dock of apps in the menu bar (with customizability)

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Robust recipes to align language models with human and AI preferences

SimPO: Simple Preference Optimization with a Reference-Free Reward

Recipes to train reward model for RLHF.

Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

Diffusion-LM

Long Context Transfer from Language to Vision

The official evaluation suite and dynamic data release for MixEval.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

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 …

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

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

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Official github repo for the paper "Compression Represents Intelligence Linearly"

OpenAI-Parallel-Toolkit is a Python library for handling multiple OpenAI API keys and parallel tasks. It provides API key rotation, multithreading for faster task execution, and utility functions t…

Mamba SSM architecture

Reference implementation for DPO (Direct Preference Optimization)

Reference implementation for DPO (Direct Preference Optimization)

A classified list of meta learning papers based on realm.