openlm-research/open_llama
OpenLLaMA provides permissively licensed open-source reproductions of Meta AI's LLaMA foundation models at 3B, 7B, and 13B scales.
★7.5k stars Language Models
Not currently ranked — collecting fresh signals.
star history
OpenLLaMA is an open-source reproduction of Meta AI’s LLaMA large language models, trained on the RedPajama dataset. The project releases PyTorch and JAX model weights for 3B, 7B, and 13B parameter variants, available as drop-in replacements for the original LLaMA models via Hugging Face transformers and EasyLM.
Frequently asked
- What is openlm-research/open_llama?
- OpenLLaMA provides permissively licensed open-source reproductions of Meta AI's LLaMA foundation models at 3B, 7B, and 13B scales.
- Is open_llama open source?
- Yes — openlm-research/open_llama is open source, released under the Apache-2.0 license.
- How popular is open_llama?
- openlm-research/open_llama has 7.5k stars on GitHub.
- Where can I find open_llama?
- openlm-research/open_llama is on GitHub at https://github.com/openlm-research/open_llama.