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 →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Together AI | $0.8 | $0.8 | Serverless | |
| Alibaba Cloud PAI-EAS | — | — | Serverless | |
| Fireworks AI | $0.90 | $0.90 | Provisioned |
Benchmark Scores(2)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HumanEval | 57.1 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 73.8 | 5-shot | Open LLM Leaderboard |
Specifications
FamilyDeepSeek Coder
Released2024-03-07
Parameters33B
Context16K
ArchitectureDecoder Only
Specializationcode
Trainingfinetuning
Fine-tuningbase
Created by
Advancing artificial general intelligence (AGI).
Hangzhou, Zhejiang, China
Founded 2023
Website