duanyu

duanyu's Stars

• ollama/ollama

  Get up and running with Llama 3.3, Phi 4, Gemma 2, and other large language models.

  Language:Go107k6155.4k8.6k

• openai/whisper

  Robust Speech Recognition via Large-Scale Weak Supervision

  Language:Python74.3k60508.9k

• comfyanonymous/ComfyUI

  The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

  Language:Python63.4k4434.3k6.8k

• run-llama/llama_index

  LlamaIndex is the leading framework for building LLM-powered agents over your data.

  Language:Python38k2545.7k5.5k

• pydantic/pydantic

  Data validation using Python type hints

  Language:Python22k1224.8k2k

• LlamaFamily/Llama-Chinese

  Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

  Language:Python14.3k1493371.3k

• openai/tiktoken

  tiktoken is a fast BPE tokeniser for use with OpenAI's models.

  Language:Python13k170245904

• LianjiaTech/BELLE

  BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

  Language:HTML8k108442765

• OpenBMB/MiniCPM

  MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

  Language:Jupyter Notebook7.3k78224464

• ymcui/Chinese-LLaMA-Alpaca-2

  中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

  Language:Python7.1k78389581

• OpenAccess-AI-Collective/axolotl

  Go ahead and axolotl questions

  Language:Python6.9k50597750

• vikhyat/moondream

  tiny vision language model

  Language:Jupyter Notebook6.6k60140529

• modelscope/agentscope

  Start building LLM-empowered multi-agent applications in an easier way.

  Language:Python5.9k32157360

• metavoiceio/metavoice-src

  Foundational model for human-like, expressive TTS

  Language:Python4k80128668

• PKU-YuanGroup/Video-LLaVA

  【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

  Language:Python3.1k29202222

• elevenlabs/elevenlabs-python

  The official Python API for ElevenLabs Text to Speech.

  Language:Python2.3k38267275

• openai/consistencydecoder

  Consistency Distilled Diff VAE

  Language:Python2.1k212076

• tatsu-lab/alpaca_eval

  An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

  Language:Jupyter Notebook1.6k8156248

• charent/ChatLM-mini-Chinese

  中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

  Language:Python1.3k1451159

• lukasschwab/arxiv.py

  Python wrapper for the arXiv API

  Language:Python1.2k1679126

• BAAI-DCAI/Bunny

  A family of lightweight multimodal models.

  Language:Python9702013074

• allenai/natural-instructions

  Expanding natural instructions

  Language:Python96621161190

• jiaeyan/Jiayan

  甲言，专注于古代汉语(古汉语/古文/文言文/文言)处理的NLP工具包，支持文言词库构建、分词、词性标注、断句和标点。Jiayan, the 1st NLP toolkit designed for Classical Chinese, supports lexicon construction, tokenizing, POS tagging, sentence segmentation and punctuation.

  Language:Python593112471

• charent/Phi2-mini-Chinese

  Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.

  Language:Jupyter Notebook51581556

• monk1337/resp

  Fetch Academic Research Papers from different sources

  Language:Python4064445

• varunshenoy/super-json-mode

  Low latency JSON generation using LLMs ⚡️

  Language:Jupyter Notebook3893514

• Mahdisadjadi/arxivscraper

  A python module to scrape arxiv.org for a date range and category

  Language:Python29091353

• Yikai-Liao/symusic

  A swift and unified toolkit for symbolic music processing

  Language:C++14243610

• briansemrau/MIDI-LLM-tokenizer

  Tools for converting .mid files into text for training large language models

  Language:Python84438

• THUNLP-MT/THUCC

  An open-source classical Chinese information processing toolkit developed by Tsinghua Natural Language Processing Group

  Language:Python48517