Vybe Guide
Sign Up

Explore Projects

Discover 10 open source projects

Active filters (1):
Search: post-trainingร—
Clear all

Showing 1-10 of 10 projects

meta-pytorch/torchtune

torchtune is a PyTorch-native post-training library for fine-tuning and tuning machine learning models.

5.7K
Active
Python
Fine-tuning
Inference
PyTorch
#machine-learning#fine-tuning#post-training

THUDM/slime

An LLM post-training framework for scaling Reinforcement Learning.

4.6K
Active
Python
LLM Frameworks
API Frameworks
Python
#reinforcement-learning#llm#post-training

allenai/open-instruct

AllenAI's open-source post-training codebase for building AI models and agents.

3.6K
Active
Python
LLM Frameworks
Agents & Orchestration
Python
#llm#language-model#ai-agent

hao-ai-lab/FastVideo

A unified inference and post-training framework for accelerated video generation powered by AI.

3.1K
Active
Python
Computer Vision
Inference
PyTorch
#video-generation#diffusion-models#distillation

thinking-machines-lab/tinker-cookbook

A Python library for post-training with the Tinker AI coding tool, focused on vibe coders.

2.9K
Active
Python
AI Code Generation
LLM Wrappers & SDKs
Python
#ai-coding#code-generation#llm-sdk

SmartFlowAI/EmoLLM

This is a large language model (LLM) focused on mental health, with pre/post-training, datasets, evaluation, and deployment tools.

1.7K
Stable
Python
LLM Frameworks
Fine-tuning
#llm#mental-health#dataset

bespokelabsai/curator

A Python library for synthetic data curation and structured data extraction for machine learning models.

1.6K
Active
Python
Synthetic Data
LLM Frameworks
Python
#machine-learning#data-generation#data-curation

mit-han-lab/smoothquant

SmoothQuant is an efficient post-training quantization tool for large language models, enabling accurate and fast inference.

1.6K
Archived
Python
LLM Frameworks
Inference
Python
#quantization#large-language-models#performance-optimization

meta-pytorch/OpenEnv

An interface library for reinforcement learning (RL) post-training with environments.

1.2K
Active
Python
Agents & Orchestration
CLI Tools
Python
#reinforcement-learning#rl#environments

JudgmentLabs/judgeval

An open-source post-building layer for AI agents, providing environment data and evaluations to power agent post-training and monitoring.

1.0K
Active
Python
Agents & Orchestration
LLM Frameworks
Python
#agent#agentic-ai#llm-evaluation

Stay in the loop

Get weekly updates on trending AI coding tools and projects.