imoneoi/openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

45
/ 100
Emerging

Employs C-RLFT (offline reinforcement learning-inspired fine-tuning) to train on mixed-quality data without preference labels, enabling competitive performance with ChatGPT-level capabilities on consumer GPUs. Available as fine-tuned Llama-based model variants (3.5-7B, 3.6-8B) via Hugging Face with comprehensive evaluation benchmarks (MT-Bench, HumanEval, MMLU, GSM8K) and reproducible evaluation scripts included in the repository.

5,476 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

5,476

Forks

433

Language

Python

License

Apache-2.0

Last pushed

Sep 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/imoneoi/openchat"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.