Fine-tuning large language models with huggingface transformers and deepspeed

Code for the paper `Text Classification via Large Language Models`.

Label, clean and enrich text datasets with LLMs.

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Reward Model framework for LLM RLHF

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

A simple yet effective loss function for face verification.

CORAL and CORN implementations for ordinal regression with deep neural networks.

Rank Consistent Ordinal Regression for Neural Networks with Application to Age Estimation

Reproduce Results for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels" https://arxiv.org/abs/1908.06112

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Zero-shot Document Ranking with Large Language Models.

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

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

A series of large language models developed by Baichuan Intelligent Technology

GLM (General Language Model)

Generative Agents: Interactive Simulacra of Human Behavior

评估自然语言的流畅度

An open-source tool-augmented conversational language model from Fudan University

Code and documentation to train Stanford's Alpaca models, and generate the data.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

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

基于ChatGLM-6B + LoRA的Fintune方案

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技