Instructions to use amd/DeepSeek-R1-0528-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/DeepSeek-R1-0528-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="amd/DeepSeek-R1-0528-BF16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amd/DeepSeek-R1-0528-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/DeepSeek-R1-0528-BF16", trust_remote_code=True)
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 Settings

vLLM

How to use amd/DeepSeek-R1-0528-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/DeepSeek-R1-0528-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/DeepSeek-R1-0528-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/DeepSeek-R1-0528-BF16

SGLang

How to use amd/DeepSeek-R1-0528-BF16 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 "amd/DeepSeek-R1-0528-BF16" \
    --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": "amd/DeepSeek-R1-0528-BF16",
		"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 "amd/DeepSeek-R1-0528-BF16" \
        --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": "amd/DeepSeek-R1-0528-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/DeepSeek-R1-0528-BF16 with Docker Model Runner:
```
docker model run hf.co/amd/DeepSeek-R1-0528-BF16
```

bowenbaoamd commited on Jan 23

Commit

159dc7b

verified ·

1 Parent(s): 498ec02

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -29,6 +29,7 @@ To enable MTP layer loading and quantization, this model is adapted from `unslot
 - When loading this model, you must set `trust_remote_code=True` to ensure that changes related to the MTP layer in `modeling_deepseek.py` take effect.
 - After loading this model with `transformers`, **evaluation should NOT be performed directly**. The reason is that the forward function for the added MTP layer in `modeling_deepseek.py` is implemented only for calibration during the quantization process, so computation is not guaranteed to be the same as the original DeepSeek-R1-0528.
 - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
 Below is an example of how to quantize this model:

 - When loading this model, you must set `trust_remote_code=True` to ensure that changes related to the MTP layer in `modeling_deepseek.py` take effect.
 - After loading this model with `transformers`, **evaluation should NOT be performed directly**. The reason is that the forward function for the added MTP layer in `modeling_deepseek.py` is implemented only for calibration during the quantization process, so computation is not guaranteed to be the same as the original DeepSeek-R1-0528.
 - Therefore, when quantizing with AMD-Quark, you **must add the `--skip_evaluation` option** to skip the evaluation step and only perform quantization.
+- To skip quantization for the MTP layers, set `exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head model.layers.61.*"`.
 Below is an example of how to quantize this model: