Pinned Repositories
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
Decoupling-Gating-From-Linearity
deep-learning-research-lab
A distributed computing infrastructure for simulations, model training & fine-tuning.
distributed-speculative-inference
The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)
embedding-projector-standalone
keyboardAnt.github.io
Personal blog about research, machine learning, deep learning, data science and software engineering.
nn-mem-vision
An infrastructure for empirical research: Studying the limits of neural networks for computer vision tasks.
nnlib
PyTorch based NN modules frequently used in various projects
wis-glucose-challenge
This is the 1st Place Winner (1 out of 45) in a data science competition led by Prof. Eran Segal on time-series forecasting via neural networks (Kaggle-like).
keyboardAnt's Repositories
keyboardAnt/distributed-speculative-inference
The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)
keyboardAnt/deep-learning-research-lab
A distributed computing infrastructure for simulations, model training & fine-tuning.
keyboardAnt/keyboardAnt.github.io
Personal blog about research, machine learning, deep learning, data science and software engineering.
keyboardAnt/Decoupling-Gating-From-Linearity
keyboardAnt/nn-mem-vision
An infrastructure for empirical research: Studying the limits of neural networks for computer vision tasks.
keyboardAnt/optimal-stopping-game
A game of probability & optimization simulating Optimal Stopping Problem variants. Supports multiple agents with different policies.
keyboardAnt/pilev2
keyboardAnt/simpleaichat
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
keyboardAnt/wis-glucose-challenge
This is the 1st Place Winner (1 out of 45) in a data science competition led by Prof. Eran Segal on time-series forecasting via neural networks (Kaggle-like).
keyboardAnt/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
keyboardAnt/ai4code_repair_workshop
AI4Code syntax repair tutorial for IAP 2023
keyboardAnt/blog
Public repo for HF blog posts
keyboardAnt/containerapps-albumapi-python
Container Apps Quickstart: Python Album API
keyboardAnt/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
keyboardAnt/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
keyboardAnt/detecting-fake-text
Giant Language Model Test Room
keyboardAnt/FinRL
FinRL: Financial Reinforcement Learning. 🔥
keyboardAnt/FinRL-Tutorials
Tutorials. Please star.
keyboardAnt/GPTQ-for-SantaCoder
4 bits quantization of SantaCoder using GPTQ
keyboardAnt/hf-bench
Benchmark TTFT, TPOT, T/s, Speedup
keyboardAnt/huggingface-demos
Personal demos using Hugging Face 🤗 tools
keyboardAnt/Implicit-Regularization-Towards-Rank-Minimization-in-ReLU-Networks--presentation
Slides to present our research paper on the foundations of deep learning, “Implicit Regularization Towards Rank Minimization in ReLU Networks”.
keyboardAnt/keyboardAnt
keyboardAnt/openai-cookbook
Examples and guides for using the OpenAI API
keyboardAnt/optimum-benchmark
A repository for benchmarking HF Optimum's optimizations for inference and training.
keyboardAnt/picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy.
keyboardAnt/smartbugs-curated
SB Curated is a curated dataset of Solidity smart contracts annotated with tagged vulnerabilities. The dataset was created to evaluate the accuracy of automated analysis tools.
keyboardAnt/speculative-sampling
Simple implementation of Speculative Sampling in NumPy for GPT-2.
keyboardAnt/TheAgentCompany
An agent benchmark with tasks in a simulated software company.
keyboardAnt/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.