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

Libraries

How to use deepseek-ai/deepseek-coder-33b-instruct with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct")
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 deepseek-ai/deepseek-coder-33b-instruct 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-33b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-33b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-coder-33b-instruct

SGLang

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

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

Failed to Deploy this model in Inference Endpoints

#19

by calvinball - opened Dec 24, 2023

Discussion

calvinball

Dec 24, 2023

Hi, I tried to deploy this model in Inference Endpoints using the Text Generation Inference , however it fails to start. When I see the logs, I found that it detects this model as PEFT model and try to load model with the AutoPEFT class. As we know this model doesn’t have any adapter weights.

Error logs

2023/12/23 17:15:48 ~ {"timestamp":"2023-12-23T10:15:48.081726Z","level":"INFO","fields":{"message":"Peft model detected.\n"},"target":"text_generation_launcher"}
2023/12/23 17:15:48 ~ {"timestamp":"2023-12-23T10:15:48.081759Z","level":"INFO","fields":{"message":"Loading the model it might take a while without feedback\n"},"target":"text_generation_launcher"}
2023/12/23 17:15:48 ~ {"timestamp":"2023-12-23T10:15:48.612560Z","level":"ERROR","fields":{"message":"Download encountered an error: Traceback (most recent call last):\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/utils/config.py\", line 117, in from_pretrained\n config_file = hf_hub_download(\n\n File \"/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py\", line 110, in _inner_fn\n validate_repo_id(arg_value)\n\n File \"/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py\", line 164, in validate_repo_id\n raise HFValidationError(\n\nhuggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: '/repository'.\n\n\nDuring handling of the above exception, another exception occurred:\n\n\nTraceback (most recent call last):\n\n File \"/opt/conda/lib/python3.10/site-packages/text_generation_server/utils/peft.py\", line 16, in download_and_unload_peft\n model = AutoPeftModelForCausalLM.from_pretrained(\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/auto.py\", line 69, in from_pretrained\n peft_config = PeftConfig.from_pretrained(pretrained_model_name_or_path, **kwargs)\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/utils/config.py\", line 121, in from_pretrained\n raise ValueError(f\"Can't find '{CONFIG_NAME}' at '{pretrained_model_name_or_path}'\")\n\nValueError: Can't find 'adapter_config.json' at '/repository'\n\n\nDuring handling of the above exception, another exception occurred:\n\n\nTraceback (most recent call last):\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/utils/config.py\", line 117, in from_pretrained\n config_file = hf_hub_download(\n\n File \"/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py\", line 110, in _inner_fn\n validate_repo_id(arg_value)\n\n File \"/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py\", line 164, in validate_repo_id\n raise HFValidationError(\n\nhuggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: '/repository'.\n\n\nDuring handling of the above exception, another exception occurred:\n\n\nTraceback (most recent call last):\n\n File \"/opt/conda/bin/text-generation-server\", line 8, in <module>\n sys.exit(app())\n\n File \"/opt/conda/lib/python3.10/site-packages/text_generation_server/cli.py\", line 204, in download_weights\n utils.download_and_unload_peft(\n\n File \"/opt/conda/lib/python3.10/site-packages/text_generation_server/utils/peft.py\", line 24, in download_and_unload_peft\n model = AutoPeftModelForSeq2SeqLM.from_pretrained(\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/auto.py\", line 69, in from_pretrained\n peft_config = PeftConfig.from_pretrained(pretrained_model_name_or_path, **kwargs)\n\n File \"/opt/conda/lib/python3.10/site-packages/peft/utils/config.py\", line 121, in from_pretrained\n raise ValueError(f\"Can't find '{CONFIG_NAME}' at '{pretrained_model_name_or_path}'\")\n\nValueError: Can't find 'adapter_config.json' at '/repository'\n\n"},"target":"text_generation_launcher","span":{"name":"download"},"spans":[{"name":"download"}]}
2023/12/23 17:15:48 ~ Error: DownloadError

Note: I already changed the container config for Quantization as None

mustafak99

Dec 27, 2023

encountered the same issue any update ?

jxji

DeepSeek org Feb 22, 2024

•

edited Feb 22, 2024

Summarized from your error log:

huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: '/repository'

and

ValueError: Can't find 'adapter_config.json' at '/repository'

I think this is the direct cause of the failure

luofuli

Feb 25, 2024

cc @zqh11

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