# DeepSeek Coder 33B Instruct

> Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.

Provider: Deepseek · Type: LLM · State: Ready

model path: `accounts/fireworks/models/deepseek-coder-33b-instruct`

[Deploy on demand](https://app.fireworks.ai/dashboard/deployments/create?baseModel=accounts/fireworks/models/deepseek-coder-33b-instruct)

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.

## DeepSeek Coder 33B Instruct API Features

- **On-demand Deployment**: On-demand deployments allow you to use DeepSeek Coder 33B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. · [Docs](https://docs.fireworks.ai/guides/ondemand-deployments)

## Metadata

- **State**: Ready
- **Created on**: 27 FEB, 2024
- **Kind**: Base model
- **Provider**: Deepseek
- **Huggingface**: [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct)

## Specifications

- **Calibrated**: No
- **Mixture-of-Experts**: No
- **Parameters**: 33.3B

## Supporting Functionality

- **Fine-tuning**: Not Supported
- **Serverless**: Not Supported
- **Context Length**: 16.3k tokens
- **Function Calling**: Not Supported
- **Embeddings**: Not Supported
- **Rerankers**: Not Supported
- **Supporting image input**: Not Supported
