LLM ReferenceLLM Reference

CodeLlama 34B

codellama-34b

Open Source

About

CodeLlama 34B is a powerful generative text model developed by Meta, specifically tailored for code synthesis and understanding. With 34 billion parameters, it excels in code completion, infilling, and instruction following, particularly for Python programming. The model utilizes an auto-regressive transformer architecture and has been trained on a diverse dataset of programming languages, making it versatile for various coding tasks. Designed for both commercial and research applications, CodeLlama 34B offers AI engineers a robust tool for integrating advanced code generation capabilities into their projects. More details can be found on the model's Hugging Face page .

CodeLlama 34B has a 100K-token context window.

CodeLlama 34B input tokens at $0.2/1M, output at $0.45/1M.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(6)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Together AI$0.8$0.8Serverless
DeepInfra$0.20$0.45Serverless
Fireworks AI$0.90$0.90Provisioned
IBM watsonx$1.8$1.8Serverless
Microsoft Foundry$1.54$1.77Provisioned
Replicate API$0.20$1.00Serverless

Benchmark Scores(1)

BenchmarkScoreVersionSource
Massive Multitask Language Understanding68.95-shotHugging Face Model Card

Rankings

Specifications

Released2023-08-24
Parameters34B
Context100K
ArchitectureDecoder Only
Knowledge cutoff2024-03
Specializationgeneral
Trainingfinetuned

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website