LLM ReferenceLLM Reference

DeepSeek Coder 33B

Open Source

About

Large code model from DeepSeek Coder with 16K context.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(3)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Together AI$0.8$0.8Serverless
Alibaba Cloud PAI-EASServerless
Fireworks AI$0.90$0.90Provisioned

Benchmark Scores(2)

BenchmarkScoreVersionSource
HumanEval57.1pass@1Open LLM Leaderboard
Massive Multitask Language Understanding73.85-shotOpen LLM Leaderboard

Rankings

Specifications

Released2024-03-07
Parameters33B
Context16K
ArchitectureDecoder Only
Specializationcode
Trainingfinetuning
Fine-tuningbase

Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website