CodeLlama-70B-Instruct

Name: CodeLlama-70B-Instruct
Author: Facebook AI Research Lab

Coding modelCodeLlama

Release date: 2024-01-30Updated: 2024-01-30Views: 539

Live demoGitHub Hugging Face Compare

Parameters

70B

Context length

100K

Multilingual

No data

Reasoning ability

No data

CodeLlama-70B-Instruct is an AI model published by Facebook AI Research Lab, released on 2024-01-30, for Coding model, with 70B parameters, and 100K context length, requiring about 140GB storage, with a 67.80 score on HumanEval.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

CodeLlama-70B-Instruct

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

100K tokens

Max output length

No data

Model type

Coding model

Modality (in / out)

No data

Release date

2024-01-30

Model file size

140GB

MoE architecture

Total params / Active params

70B / Not applicable

Knowledge cutoff

No data

CodeLlama-70B-Instruct

Open source & experience

Code license

Weights license

- Commercial use permitted

GitHub repo

github.com/facebookresearch/codellama

Hugging Face

huggingface.co/codellama/CodeLlama-70b-hf

Live demo

N/A

CodeLlama-70B-Instruct

Official resources

Paper

DataLearnerAI blog

N/A

CodeLlama-70B-Instruct

API details

API speed

No data

No public API pricing yet.

CodeLlama-70B-Instruct

Benchmark Results

CodeLlama-70B-Instruct currently shows benchmark results led by HumanEval (60 / 140, score 67.80), MBPP (49 / 96, score 62.20). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.