Instructions to use TheBloke/deepseek-coder-33B-instruct-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/deepseek-coder-33B-instruct-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/deepseek-coder-33B-instruct-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/deepseek-coder-33B-instruct-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/deepseek-coder-33B-instruct-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/deepseek-coder-33B-instruct-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/deepseek-coder-33B-instruct-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/deepseek-coder-33B-instruct-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/deepseek-coder-33B-instruct-GPTQ

SGLang

How to use TheBloke/deepseek-coder-33B-instruct-GPTQ 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 "TheBloke/deepseek-coder-33B-instruct-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/deepseek-coder-33B-instruct-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "TheBloke/deepseek-coder-33B-instruct-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/deepseek-coder-33B-instruct-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/deepseek-coder-33B-instruct-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/deepseek-coder-33B-instruct-GPTQ
```

TheBloke commited on Nov 5, 2023

Commit

de1dd72

1 Parent(s): 5f65f95

Upload README.md

Browse files

Files changed (1) hide show

README.md +3 -10

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ license_link: LICENSE
 license_name: deepseek
 model_creator: DeepSeek
 model_name: Deepseek Coder 33B Instruct
-model_type: llama
 prompt_template: '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
@@ -74,15 +74,8 @@ You are an AI programming assistant, utilizing the Deepseek Coder model, develop
 ```
 <!-- prompt-template end -->
-<!-- licensing start -->
-## Licensing
-The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
-As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
-In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [DeepSeek's Deepseek Coder 33B Instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct).
-<!-- licensing end -->
 <!-- README_GPTQ.md-compatible clients start -->
 ## Known compatible clients / servers
@@ -392,9 +385,9 @@ And thank you again to a16z for their generous grant.
 ### 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.

 license_name: deepseek
 model_creator: DeepSeek
 model_name: Deepseek Coder 33B Instruct
+model_type: deepseek
 prompt_template: '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
 ```
 <!-- prompt-template end -->
 <!-- README_GPTQ.md-compatible clients start -->
 ## Known compatible clients / servers
 ### 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.