ldh127's repositories
AiStackAll
算法全栈之路
360zhinao
360zhinao
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
AnimeGANv2_Tensorflow2
Implementing AnimeGANv2 with Tensorflow2
chain-of-knowledge
[ICLR2024] Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
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
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
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。
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
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
google-translate-open-api
A free and unlimited API for Google Translate(support single text and Multi-segment text) 💵🚫
KamTube.py
Downloads videos from YouTube via Invidious using Python
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
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。
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
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.
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
Pai-Megatron-Patch
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
trending_archive
a Archive of the github daily trending information
trulens
Evaluation and Tracking for LLM Experiments
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
xtuner
XTuner is a toolkit for efficiently fine-tuning LLM
zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)