imoneoi/openchat

Health v2 · maintenance only

Adoption not part of the score

5490 stars · 430 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenChat is a library of open-source large language models fine-tuned with C-RLFT, an offline reinforcement learning strategy that learns from mixed-quality data without preference labels. It includes training and evaluation code plus model weights (e.g., OpenChat 3.6 based on Llama 3) that run on consumer GPUs.

Use cases

• fine-tune an open-source chat llm on mixed-quality data
• run a 7b chatgpt-quality model on a consumer gpu
• reproduce llm benchmark evaluations like gpt4 correct
• train a chat model without preference labels
• download openchat model weights for local inference

When to choose

• you want high-performing open chat models with permissive Apache-2.0 licensing
• you need to train or evaluate chat llms using the C-RLFT method
• you have limited GPU resources but need strong conversational performance

When to avoid

• you need a hosted chat API rather than self-hosted model weights
• you require the latest actively developed LLM training framework
• you need multimodal or non-chat model capabilities

Facets

library · maturity maintenance

llm-training machine-learning llm-inference large-language-models deep-learning artificial-intelligence python open-source-llm c-rlft fine-tuning chat-models reinforcement-learning gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="imoneoi/openchat")