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

Libraries

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

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

pipe = pipeline("text-generation", model="TheBloke/deepseek-coder-33B-instruct-AWQ")
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-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/deepseek-coder-33B-instruct-AWQ")
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-AWQ 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-AWQ"
# 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-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use TheBloke/deepseek-coder-33B-instruct-AWQ 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-AWQ" \
    --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-AWQ",
		"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-AWQ" \
        --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-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Getting InvalidHeaderDeserialization trying to load this model

by neilb - opened Nov 5, 2023

Discussion

neilb

Nov 5, 2023

I'm running the sample code provided on the Model card using the latest version of AutoAWQ and it crashes on the load model step:

Load model

model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
trust_remote_code=False, safetensors=True)

safetensors_rust.SafetensorError: Error while deserializing header: InvalidHeaderDeserialization

Yhyu13

Nov 5, 2023

@TheBloke Could you varify this error?

i will be waiting the GPTQ version instead

TheBloke

Owner Nov 5, 2023

Sorry about that, it was caused by a bug that resulted in there being an empty model.safetensors file as well as model-x-of-y.safetensors files as well

I've removed the bad file. If you also delete model.safetensors from your local download directory, or delete the whole folder and do a download again, it will work fine now

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment