ldh127's repositories

OpenRLHF

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

License:Apache-2.0Stargazers:0Issues:0Issues:0

trulens

Evaluation and Tracking for LLM Experiments

License:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

charset_mnbvc

本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作

License:MITStargazers:0Issues:0Issues:0

chain-of-knowledge

[ICLR2024] Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

License:MITStargazers:0Issues:0Issues:0

trending_archive

a Archive of the github daily trending information

License:MITStargazers:0Issues:0Issues:0

opencompass

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.

License:Apache-2.0Stargazers:0Issues:0Issues:0

Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

License:Apache-2.0Stargazers:0Issues:0Issues:0

xtuner

XTuner is a toolkit for efficiently fine-tuning LLM

License:Apache-2.0Stargazers:0Issues:0Issues:0

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

License:Apache-2.0Stargazers:0Issues:0Issues:0

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

License:Apache-2.0Stargazers:0Issues:0Issues:0

360zhinao

360zhinao

License:Apache-2.0Stargazers:0Issues:0Issues:0

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

License:Apache-2.0Stargazers:0Issues:0Issues:0

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

License:Apache-2.0Stargazers:0Issues:0Issues:0

Firefly

Firefly: 大模型训练工具,支持训练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

Stargazers:0Issues:0Issues:0

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

License:Apache-2.0Stargazers:0Issues:0Issues:0

zero_nlp

中文nlp解决方案(大模型、数据、模型、训练、推理)

License:MITStargazers:0Issues:0Issues:0

Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。

License:Apache-2.0Stargazers:0Issues:0Issues:0

llms_tool

一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。

License:Apache-2.0Stargazers:0Issues:0Issues:0

finetune-gpt2xl

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

License:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0

KamTube.py

Downloads videos from YouTube via Invidious using Python

License:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

AiStackAll

算法全栈之路

Stargazers:1Issues:0Issues:0

AnimeGANv2_Tensorflow2

Implementing AnimeGANv2 with Tensorflow2

Stargazers:0Issues:0Issues:0

blog

side project blog

Language:HTMLLicense:MITStargazers:0Issues:0Issues:0

google-translate-open-api

A free and unlimited API for Google Translate(support single text and Multi-segment text) 💵🚫

License:Apache-2.0Stargazers:0Issues:0Issues:0

WeRoBot

WeRoBot 是一个微信公众号开发框架

License:MITStargazers:0Issues:0Issues:0

daily_fresh

天天生鲜电商项目,技术栈:web框架:Django,异步任务处理:celery, 分布式文件存储系统:fastDFS+Nginx, 全局检索:haystack+whoosh+jieba,数据库:MySQL,缓存服务器:redis

Stargazers:0Issues:0Issues:0

izone

django+bootstrap4 个人博客

License:MITStargazers:0Issues:0Issues:0