LLM ReferenceLLM Reference

CodeLlama 70B

codellama-70b

Deprecated
Open Source

About

CodeLlama 70B is a state-of-the-art generative text model by Meta, specifically designed for code synthesis and understanding. It utilizes an auto-regressive transformer architecture and has been fine-tuned with up to 16,000 tokens, supporting inference with up to 100,000 tokens. The model excels in code completion, infilling, and instruction following, making it versatile for various programming languages and applications. With 70 billion parameters, it offers advanced capabilities for general code generation tasks, while also providing specialized variants for Python and instruction-following. Intended for both commercial and research use, CodeLlama 70B aims to assist developers in generating code, understanding programming concepts, and enhancing productivity in software development .

CodeLlama 70B has a 16K-token context window.

CodeLlama 70B input tokens at $0.45/1M, output at $0.65/1M.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(6)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Together AI$0.9$0.9Serverless
NVIDIA NIMProvisioned
DeepInfra$0.45$0.65Serverless
Fireworks AI$0.90$0.90Provisioned
Microsoft Foundry$3.78$11.34Provisioned
Replicate API$0.65$2.75Serverless

Specifications

Released2024-01-29
Parameters70B
Context16K
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuned

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website