Instructions to use Intel/deepseek-coder-1.3b_base_ov_int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/deepseek-coder-1.3b_base_ov_int8 with Transformers:

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

pipe = pipeline("text-generation", model="Intel/deepseek-coder-1.3b_base_ov_int8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/deepseek-coder-1.3b_base_ov_int8")
model = AutoModelForCausalLM.from_pretrained("Intel/deepseek-coder-1.3b_base_ov_int8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intel/deepseek-coder-1.3b_base_ov_int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/deepseek-coder-1.3b_base_ov_int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/deepseek-coder-1.3b_base_ov_int8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Intel/deepseek-coder-1.3b_base_ov_int8

SGLang

How to use Intel/deepseek-coder-1.3b_base_ov_int8 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 "Intel/deepseek-coder-1.3b_base_ov_int8" \
    --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": "Intel/deepseek-coder-1.3b_base_ov_int8",
		"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 "Intel/deepseek-coder-1.3b_base_ov_int8" \
        --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": "Intel/deepseek-coder-1.3b_base_ov_int8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intel/deepseek-coder-1.3b_base_ov_int8 with Docker Model Runner:
```
docker model run hf.co/Intel/deepseek-coder-1.3b_base_ov_int8
```

kumarijy commited on May 22, 2024

Commit

956a3d2

verified ·

1 Parent(s): ddd8ddd

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ Intended to be used with:
 - **Model type:** text generation model
 - **Language(s):** English
-- **License:** This model is licensed under the MIT License. The use of DeepSeek Coder model is subject to the model License. DeppSeek Coder supports commercial use. See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
 - **Model Summary:** deepseek-coder-1.3b-base is a 1.3B parameter model with Multi-Head Attention trained on 1 trillion tokens.
-- **Resources for more information:** [deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base), [Paper](https://arxiv.org/abs/2401.14196).
 # Uses
@@ -31,7 +31,7 @@ DeepSeek-Coder models are under a permissive license that allows for both resear
 - Code Insertion
 - Repository Level Code Completion
-### use base restrictions
 You agree not to use the Model or Derivatives of the Model:

 - **Model type:** text generation model
 - **Language(s):** English
+- **License:** This model is licensed under the MIT License. The use of DeepSeek Coder model is subject to the model License. See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
 - **Model Summary:** deepseek-coder-1.3b-base is a 1.3B parameter model with Multi-Head Attention trained on 1 trillion tokens.
+- **Resources for more information:** [deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base),  [Paper](https://arxiv.org/abs/2401.14196).
 # Uses
 - Code Insertion
 - Repository Level Code Completion
+### Use base restrictions
 You agree not to use the Model or Derivatives of the Model: