gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Your Fully-Automated Personal AI Assistant, and Open-Source & Cost-Efficient Alternative to OpenAI's Deep Research

SOTA RL fine-tuning solution for advanced math reasoning of LLM

总结Prompt&LLM论文，开源数据&模型，AIGC应用

"Improving Mathematical Reasoning with Process Supervision" by OPENAI

[KDD'2024] "HiGPT: Heterogenous Graph Language Models"

Must-read Papers on LLM Agents.

RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a …

What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

The Open Source RAG framework

顾名思义：手搓的RAG

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

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Mixtral-8x7B、Zephyr、Mistral、Aquila2、Baichuan2、CodeLlama、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型

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。

✨✨Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

收集和梳理垂直领域的开源模型、数据集及评测基准。

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

Must-read Papers on Large Language Model (LLM) Continual Learning

本人的科研经验

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

A curated list of multi party computation resources and links.

An open-source conversational language model developed by the Knowledge Works Research Laboratory at Fudan University.