KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
Repository Index
109,091 visible repositories in the index
961–984 of 1,642 · Most stars
The repository host gives no description.
Attention is all you need implementation
- attention-is-all-you-need
- paper-implementations
- pytorch
- transformer
Roblox Foundation Model for 3D Intelligence
- 3d
- shape-generation
- text-to-3d
- 3d-generation
Notebooks for the third edition of Think Stats
- data-science
- jupyter-book
- pandas
- python
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
USC urban data science course series in Python
- usc
- urban-data-science
- course-materials
- data-science
机械臂+大模型+多模态=人机协作具身智能体
Useful scripts, udfs, views, and other utilities for migration and data warehouse operations in BigQuery.
- bigquery
- google-cloud-platform
- data-warehouse
- sql
Code, data, and instructions for mapping orbits of asteroids in the solar system
An implementation of a complete machine learning solution in Python on a real-world dataset. This project is meant to demonstrate how all the steps of a machine learning pipeline come together to solve a problem!
:art: 数学公式识别增强版:中英文手写印刷公式、支持初级符号推导(数据结构基于 LaTeX 抽象语法树)Math Formula OCR Pro, supports handwrite, Chinese-mixed formulas and simple symbol reasoning (based on LaTeX AST).
- ocr
- latex
- deep-learning
- seq2seq
MovieLens based recommender system.使用MovieLens数据集训练的电影推荐系统。
Go from no deep learning knowledge to implementing GPT.
- deep-learning
- python
- pytorch
- tutorial
Instructional notebooks on music information retrieval.
- ipython-notebook
- music-information-retrieval
- python
- machine-learning
The repository host gives no description.
Efficient computing methods developed by Huawei Noah's Ark Lab
- knowledge-distillation
- model-compression
- binary-neural-networks
- pruning
https://www.sc-best-practices.org
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
- captioning
- vlm
- joycaption
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
- deep-learning
- activation-functions
- mathematics
- neural-networks
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
- machine-learning
- therapeutics
- drug-discovery
- datasets
Automatic 2D-to-3D Video Conversion with CNNs
Repository for the free online book Machine Learning from Scratch (link below!)
Lectures for INFO8010 Deep Learning, ULiège