Rlhf Python Packages

whileai

Scientific RL and SFT post-training for AI agents: build evals that can fail, simulate situations, judge checked against people, pass@1 with a 95% interval, train with GRPO/SFT/DPO, prove every gain on a held-out set. uv add whileai

zeroproof

Scientific RL and SFT post-training for AI agents: build evals that can fail, simulate situations, judge checked against people, pass@1 with a 95% interval, train with GRPO/SFT/DPO, prove every gain on a held-out set. uv add whileai

llamafactory

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

dtflow

Inspect, clean, transform and ship LLM training data from one CLI; dt view is the interactive entry point.

mlx-lm-lora

Train Large Language Models on MLX.

image-reward

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

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.

kiln-ai

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

transformerlab

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

ml-dash

Scalable Training Telemetry and Metrics Visualization

py-openjudge

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

kiln-server

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

rubrix

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

trloom

YAML-driven end-to-end fine-tuning on Hugging Face TRL — one config for model, dataset, W&B, and Modal GPUs.

log10-io

Python client library for improving your LLM app accuracy

argilla-server

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.

langchain-crusoe

The Crusoe Developer Hub is the technical home for developers building AI applications and infrastructure on Crusoe Cloud. We publish three kinds of content here: foundational lessons that explain how things work, runnable examples that complete a task end to end, and integrations that connect Crusoe to the tools you already use.

openpo

Synthetic data for fine tuning LLM

llmtuner

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

oat-llm

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

textrl

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

mlflow-crusoe

The Crusoe Developer Hub is the technical home for developers building AI applications and infrastructure on Crusoe Cloud. We publish three kinds of content here: foundational lessons that explain how things work, runnable examples that complete a task end to end, and integrations that connect Crusoe to the tools you already use.

trinity-rft

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