• 3
• 0
• 0

rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

• 2
• 0
• 0

xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

• 2
• 0
• 0

hmtl

🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP

• 2
• 0
• 0

pipeline-rl-cmu

• 2
• 0
• 0

PipelineRL

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

• 2
• 0
• 0

DeepEP

DeepEP: an efficient expert-parallel communication library

• 2
• 0
• 0

finepdfs

Codebase for FinePDFs

• 2
• 0
• 0

hf-mcp-server

Hugging Face MCP Server

• 2
• 0
• 0

jupyter-agent

Training LLMs to reason and analyze data with notebooks

• 2
• 0
• 0

boomtitan

fork of torchtitan for the boom project

• 2
• 0
• 0

torchtitan

A PyTorch native platform for training generative AI models

• 2
• 0
• 0

tau2-bench

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

• 2
• 0
• 0

lora-fast

Minimal repository to demonstrate fast LoRA inference with Flux family of models.

• 2
• 0
• 0

finetrainers

Scalable and memory-optimized training of diffusion models

• 2
• 0
• 0

responses.js

A lightweight express.js server implementing OpenAI’s Responses API, built on top of Chat Completions, powered by Hugging Face Inference Providers.

• 2
• 0
• 0

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

• 2
• 0
• 0

flux-fast

Making Flux go brrr on GPUs.

• 2
• 0
• 0

vllm-dca

A high-throughput and memory-efficient inference and serving engine for LLMs

• 2
• 0
• 0

hf-nix

• 2
• 0
• 0

prime

prime is a framework for efficient, globally distributed training of AI models over the internet.