LLaMA-Pro-8B(huggingface.co)

75 points by tosh 2 years ago | 23 comments

LiteLlama-460M-1T has 460M parameters trained with 1T tokens(huggingface.co)

34 points by dmezzetti 2 years ago | 13 comments

OpenLLaMA 13B Released(huggingface.co)

158 points by tosh 3 years ago | 78 comments

Qwen3 30B-A3B(huggingface.co)

43 points by tosh 1 year ago | 9 comments

MonadGPT – What would have happened if ChatGPT was invented in the 17th century?(huggingface.co)

282 points by surprisetalk 2 years ago | 96 comments

Show HN: Penny-1.7B Irish Penny Journal style transfer(huggingface.co)

139 points by deepsquirrelnet 1 year ago | 71 comments

Code Llama, a state-of-the-art large language model for coding(ai.meta.com)

602 points by nickthegreek 3 years ago | 236 comments

Meta newsroom post from August 24, 2023 announcing Code Llama, a large language model for generating and discussing code.

The Llama 4 herd(ai.meta.com)

1174 points by georgehill 1 year ago | 600 comments

Meta's announcement of the Llama 4 model family (Scout, Maverick, Behemoth), displayed as a stylized directory index listing models, sizes, and docs.

Code Llama, a state-of-the-art large language model for coding(ai.meta.com)

911 points by marcopicentini 3 years ago | 74 comments

Meta AI blog post from August 24, 2023 announcing Code Llama, a large language model for code generation built on Llama 2.

Qwen3.8-2.4T(huggingface.co)

692 points by Philpax 2 months ago | 161 comments

Hugging Face model card for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter mixture-of-experts text generation model from Qwen in Transformers format.

Guide to running Llama 2 locally(replicate.com)

573 points by bfirsh 3 years ago | 153 comments

Replicate blog post explaining how to run Meta's Llama 2 model locally on M1/M2 Macs, Windows, Linux, and phones without an internet connection.

GLM-4.7-Flash(huggingface.co)

323 points by scrlk 9 months ago | 108 comments

Hugging Face model card for GLM-4.7-Flash, a 31B-parameter MIT-licensed text generation model from Z.ai (zai-org).