From the source

Code Llama: Llama 2 learns to code

New model

Image published with the post by Hugging Face — Image from huggingface.co

Meta released Code Llama, a family of open-access code-specialized models based on Llama 2, with sizes 7B, 13B, and 34B parameters, including base, Python specialist, and instruct variants, trained on 500B tokens of code data, with a 16k context window (extrapolatable to 100k), and integrated into the Hugging Face ecosystem.

From the source
Code Llama is a family of state-of-the-art, open-access versions of Llama 2 specialized on code tasks
huggingface.co

Other stories

Hugging Face· 8 Oct

The model that didn't exist, so you made it yourself

A user creates six custom models via ML Intern in days

Hugging Face· 2 OctResearch paper

AutoSynthData: Generating Training Data for Enterprise Agents

Turning model failures into training data for enterprise agents

Announced: 25 Aug 2023
Detected: 03 Aug 2026 21:12 UTC (+1073d after)
License: same permissive community license as Llama 2

ModelsCode Llama

Visit source ↗huggingface.co

Hugging Face

· 30 Sep

Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning

Objective metrics for TTS evaluation, complementing human preference arenas.

Replicate· 14 Aug

A guide to prompting Llama 2

Spread Your Wings: Falcon 180B is here
Falcon 180B, the largest openly available LLM, is released on HuggingFace.
TII· 6 SepNew model
LG AI Talk Concert 2023, Large-Scale AI EXAONE 2.0 Unveiled for the First Time
LG AI Research unveils EXAONE 2.0, a large-scale multimodal AI with cost and efficiency gains.
LG AI Research· 7 AugNew model