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

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
```

Model Overview

Model Architecture: DeepSeek-R1-0528
- Input: Text
- Output: Text
Supported Hardware Microarchitecture: AMD MI350/MI355
ROCm: 7.0
PyTorch: 2.8.0
Transformers: 4.56.1
Operating System(s): Linux
Inference Engine: SGLang/vLLM

Model Details

In the original modeling_deepseek.py file from the unsloth/DeepSeek-R1-0528-BF16 model, there is no definition or implementation of the MTP (Multi-Token-Predictor) layer. As a result, when you load the original model, there is no MTP layer included, and MTP-specific quantization cannot be performed.

To enable MTP layer loading and quantization, this model is adapted from unsloth/DeepSeek-R1-0528-BF16 by adding an MTP layer in the modeling_deepseek.py file. With this modification, it is possible to use AMD-Quark to quantize the DeepSeek-R1-0528 model with the MTP layer included.

Important Notes:

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:

cd Quark/examples/torch/language_modeling/llm_ptq/
exclude_layers="lm_head *self_attn* *mlp.gate *eh_proj *shared_head.head" 
python3 quantize_quark.py --model_dir $MODEL_DIR \
                          --quant_scheme w_mxfp4_a_mxfp4 \
                          --num_calib_data 32 \
                          --output_dir $output_dir \
                          --exclude_layers $exclude_layers \
                          --dataset pileval \
                          --multi_gpu \
                          --model_export hf_format \
                          --trust_remote_code \
                          --skip_evaluation \
                          --seq_len 512

For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.

License

Downloads last month: 5

Safetensors

Model size

684B params

Tensor type

F32

BF16

Model tree for amd/DeepSeek-R1-0528-BF16

Base model

deepseek-ai/DeepSeek-R1-0528

Finetuned

unsloth/DeepSeek-R1-0528-BF16

Finetuned

(1)

this model