Instructions to use deepseek-ai/deepseek-coder-5.7bmqa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-coder-5.7bmqa-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-coder-5.7bmqa-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-5.7bmqa-base")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-5.7bmqa-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/deepseek-coder-5.7bmqa-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-coder-5.7bmqa-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-5.7bmqa-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-coder-5.7bmqa-base

SGLang

How to use deepseek-ai/deepseek-coder-5.7bmqa-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepseek-ai/deepseek-coder-5.7bmqa-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-5.7bmqa-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepseek-ai/deepseek-coder-5.7bmqa-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-5.7bmqa-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-coder-5.7bmqa-base with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-coder-5.7bmqa-base
```

guoday commited on Nov 1, 2023

Commit

1c90537

1 Parent(s): a5db2fc

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ Deepseek Coder comprises a series of code language models trained on both 87% co
 - **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 1B, 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.
@@ -167,8 +167,6 @@ outputs = model.generate(**inputs, max_new_tokens=140)
 print(tokenizer.decode(outputs[0]))
 ```
----
-In the following scenario, the Deepseek-Coder 7B model effectively calls a class **IrisClassifier** and its member function from the `model.py` file, and also utilizes functions from the `utils.py` file, to correctly complete the **main** function in`main.py` file for model training and evaluation.
 ### 4. Lincense

 - **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.
 print(tokenizer.decode(outputs[0]))
 ```
 ### 4. Lincense