Lists (1)
Stars
Firefly: 大模型训练工具，支持训练Qwen2.5、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
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.
中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。
Google Cloud Client Library for Python
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and…
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
使用Bert，ERNIE，进行中文文本分类
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
The simplest, fastest repository for training/finetuning small-sized VLMs.
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
My learning notes/codes for ML SYS.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
An Open-Source Package for Knowledge Embedding (KE)
A non-validating SQL parser module for Python
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
中文langchain项目|小必应，Q.Talk，强聊，QiangTalk
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
slime is an LLM post-training framework for RL Scaling.