Hugging Face's logo

deepseek-ai
/
deepseek-coder-33b-instruct

Text Generation
Transformers
PyTorch
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
29
deepseek-coder-33b-instruct / README.md
guoday's picture
guoday
Update README.md
3053526
preview code
|
raw
history blame
3.49 kB
metadata
license: other
license_name: deepseek
license_link: LICENSE

1. Introduction of Deepseek Coder

Deepseek Coder comprises a series of code language models trained on both 87% code and 13% natural language in English and Chinese, with each model pre-trained on 2T tokens. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.

  • Massive Training Data: Trained on 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages.

  • Highly Flexible & Scalable: Offered in model sizes of 1.3B, 5.7B, 6.7B, and 33B, enabling users to choose the setup most suitable for their requirements.

  • Superior Model Performance: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks.

  • Advanced Code Completion Capabilities: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks.

2. Model Summary

deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.

3. How to Use

Here give some examples of how to use our model.

Chat Model Inference 

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-coder-33b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-coder-33b-instruct", trust_remote_code=True).cuda()
system_prompt = "You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\n"
messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
prompt = system_prompt
for content in messages:
    if content['role'] == 'user':
        prompt += f"### Instruction:\n{content['content']}\n"
    else:
        prompt += f"### Response:\n{content['content']}\n"
        prompt += "<|EOT|>\n"
prompt += "### Response:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
# 32021 is the id of <|EOT|> token
outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=32021)
print(tokenizer.decode(outputs[0]))

4. Lincense

This code repository is licensed under the MIT License. The use of DeepSeek Coder model and weights is subject to the Model License. DeepSeek Coder supports commercial use.

See the LICENSE-MODEL for more details.

5. Contact

If you have any questions, please raise an issue or contact us at agi_code@deepseek.com.