benkerd22

benkerd22's Stars

• streamlit/streamlit

  Streamlit — A faster way to build and share data apps.

  Language:Python36.8k3.2k

• open-compass/VLMEvalKit

  Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks

  Language:Python1.7k242

• taichi-dev/taichi

  Productive, portable, and performant GPU programming in Python.

  Language:C++26.6k2.3k

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.8k182

• ChatGPTNextWeb/NextChat

  ✨ Local and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

  Language:TypeScript78.8k60.1k

• oobabooga/text-generation-webui

  A Gradio web UI for Large Language Models with support for multiple inference backends.

  Language:Python41.7k5.4k

• microsoft/SparseMixer

  Sparse Backpropagation for Mixture-of-Expert Training

  Language:Python275

• nodeca/pako

  high speed zlib port to javascript, works in browser & node.js

  Language:JavaScript5.7k792

• alibaba/BizCharts

  Powerful data visualization library based on G2 and React.

  Language:TypeScript6.2k672

• Alex313031/thorium

  Chromium fork named after radioactive element No. 90. Windows and MacOS/Raspi/Android/Special builds are in different repositories, links are towards the top of the README.md.

  Language:C++5.2k160

• xonsh/xonsh

  :shell: Python-powered shell. Full-featured and cross-platform.

  Language:Python8.5k651

• kbuzzard/xena

  Lean Library currently studying for a degree at Imperial College

  Language:Lean22722

• ImperialCollegeLondon/natural_number_game

  Building the natural numbers in Lean 3. The original natural number game, now frozen. See README for Lean 4 information.

  Language:Lean29473

• libfuse/sshfs

  A network filesystem client to connect to SSH servers

  Language:C6.2k502

• gradio-app/gradio

  Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

  Language:Python35.4k2.7k

• tensorchord/Awesome-LLMOps

  An awesome & curated list of best LLMOps tools for developers

  Language:Shell4.3k417

• aimhubio/aim

  Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

  Language:Python5.3k330

• NVIDIA/TransformerEngine

  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

  Language:Python2.1k349

• Textualize/rich

  Rich is a Python library for rich text and beautiful formatting in the terminal.

  Language:Python50.4k1.8k

• open-compass/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.

  Language:Python4.5k481

• aliyun/oss-browser

  OSS Browser 提供类似windows资源管理器功能。用户可以很方便的浏览文件，上传下载文件，支持断点续传等。

  Language:JavaScript3.3k462

• huggingface/text-generation-inference

  Large Language Model Text Generation Inference

  Language:Python9.6k1.1k

• haonan-li/CMMLU

  CMMLU: Measuring massive multitask language understanding in Chinese

  Language:Python71661

• tqdm/tqdm

  :zap: A Fast, Extensible Progress Bar for Python and CLI

  Language:Python29.1k1.4k

• openai/evals

  Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

  Language:Python15.4k2.6k

• EleutherAI/gpt-neox

  An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

  Language:Python7k1k

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python7.5k2k

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python11.1k2.5k

• BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

  Language:Python13k883

• CLUEbenchmark/SuperCLUE

  SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

  3.1k100