• license: other
• license_name: deepseek
• license_link: LICENSE
• tasks:
  • code-generation

Model Card for DeepSeek-Coder-33B

[🏠Homepage] | [🤖 Chat with DeepSeek Coder] | [Discord] | [Wechat(微信)]

Model Description

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. 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.

• 33 billion parameter model ollama run vitoreafeliciano/deepseek-coder

CLI

Open the terminal and run ollama run vitoreafeliciano/deepseek-coder

API

Example using curl:

 -X POST http://localhost:11434/api/generate -d '{
  "model": "vitoreafeliciano/deepseek-coder",
  "prompt":"Why is the sky blue?"
 }'

API documentation

References

HuggingFace

Howto

mkdir huggingface
cd huggingface
pip install huggingface_hub

download.py

from huggingface_hub import snapshot_download
model_id="deepseek-ai/deepseek-coder-33b-instruct"
snapshot_download(repo_id=model_id, local_dir="deepseek-coder-33b",
                  local_dir_use_symlinks=False, revision="main")

python download.py

llama.cpp

cd ..
git clone https://github.com/ggerganov/llama.cpp/tree/master
cd llama.cpp
pip install -r requirements.txt
cd ..

cd huggingface
python ../llama.cpp/convert_hf_to_gguf.py deepseek-coder-33b --outfile deepseek-coder-33b.gguf --outtype auto 

get llama.cpp windows x64 ubuntu x64 extract and add to PATH

llama-quantize deepseek-coder-33b.gguf deepseek-coder-33b-q4_0.gguf Q4_0
ollama create deepseek-coder
ollama run deepseek-coder
ollama push user/deepseek-coder

1. Introduction of Deepseek Coder

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. 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 from scratch 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. - Home Page: DeepSeek - Repository: deepseek-ai/deepseek-coder - Chat With DeepSeek Coder: DeepSeek-Coder

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-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
# tokenizer.eos_token_id is the id of <|EOT|> token
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))

4. License

This code repository is licensed under the MIT License. The use of DeepSeek Coder models 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.