Rlhf Python Packages

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

transformerlab

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

image-reward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

rubrix

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

transformerlab-cli

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

shadowlm

A fine-tuning SDK — any open model, any harness, any method. 12 training methods behind one argument; pure-stdlib core.

trinity-rft

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

mlx-lm-lora

Train Large Language Models on MLX.

py-openjudge

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

kiln-ai

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

argilla-server

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

llmtuner

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

kiln-server

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

log10-io

Unified LLM data management

textrl

TextRL - reinforcement learning for text generation, built on HuggingFace TRL.

oat-llm

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

pairjudge

Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.

lazyllm-llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

openpo

Synthetic data for fine tuning LLM

glmtuner

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

alignment-handbook

The Alignment Handbook

knowlyr-datalabel

Serverless annotation framework with LLM pre-labeling, inter-annotator agreement analysis & offline HTML interface. CLI + MCP ready.

oxrl

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.

lmxlab

Transformer language models on Apple Silicon with MLX