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

Libraries

How to use deepseek-ai/DeepSeek-R1 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1", 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("deepseek-ai/DeepSeek-R1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1", 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1"
# 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-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1

SGLang

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

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1
```

msr2000 commited on Mar 27, 2025

Commit

56d4cbb

1 Parent(s): a157fa3

Small fix

Browse files

Files changed (3) hide show

config.json +0 -3
configuration_deepseek.py +0 -11
modeling_deepseek.py +1 -2

config.json CHANGED Viewed

@@ -9,7 +9,6 @@
     "AutoModel": "modeling_deepseek.DeepseekV3Model",
     "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
   },
-  "aux_loss_alpha": 0.001,
   "bos_token_id": 0,
   "eos_token_id": 1,
   "ep_size": 1,
@@ -32,7 +31,6 @@
   "num_hidden_layers": 61,
   "num_key_value_heads": 128,
   "num_nextn_predict_layers": 1,
-  "pretraining_tp": 1,
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
@@ -58,7 +56,6 @@
   "rope_theta": 10000,
   "routed_scaling_factor": 2.5,
   "scoring_func": "sigmoid",
-  "seq_aux": true,
   "tie_word_embeddings": false,
   "topk_group": 4,
   "topk_method": "noaux_tc",

     "AutoModel": "modeling_deepseek.DeepseekV3Model",
     "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "bos_token_id": 0,
   "eos_token_id": 1,
   "ep_size": 1,
   "num_hidden_layers": 61,
   "num_key_value_heads": 128,
   "num_nextn_predict_layers": 1,
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "rope_theta": 10000,
   "routed_scaling_factor": 2.5,
   "scoring_func": "sigmoid",
   "tie_word_embeddings": false,
   "topk_group": 4,
   "topk_method": "noaux_tc",

configuration_deepseek.py CHANGED Viewed

@@ -82,11 +82,6 @@ class DeepseekV3Config(PretrainedConfig):
             Beginning of stream token id.
         eos_token_id (`int`, *optional*, defaults to 2):
             End of stream token id.
-        pretraining_tp (`int`, *optional*, defaults to 1):
-            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
-            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
-            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
-            issue](https://github.com/pytorch/pytorch/issues/76232).
         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         rope_theta (`float`, *optional*, defaults to 10000.0):
@@ -141,8 +136,6 @@ class DeepseekV3Config(PretrainedConfig):
         first_k_dense_replace = 3,
         norm_topk_prob = True,
         scoring_func = 'sigmoid',
-        aux_loss_alpha = 0.001,
-        seq_aux = True,
         hidden_act="silu",
         max_position_embeddings=4096,
         initializer_range=0.02,
@@ -151,7 +144,6 @@ class DeepseekV3Config(PretrainedConfig):
         pad_token_id=None,
         bos_token_id=0,
         eos_token_id=1,
-        pretraining_tp=1,
         tie_word_embeddings=False,
         rope_theta=10000.0,
         rope_scaling=None,
@@ -184,8 +176,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.first_k_dense_replace = first_k_dense_replace
         self.norm_topk_prob = norm_topk_prob
         self.scoring_func = scoring_func
-        self.aux_loss_alpha = aux_loss_alpha
-        self.seq_aux = seq_aux
         # for backward compatibility
         if num_key_value_heads is None:
             num_key_value_heads = num_attention_heads
@@ -194,7 +184,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.hidden_act = hidden_act
         self.initializer_range = initializer_range
         self.rms_norm_eps = rms_norm_eps
-        self.pretraining_tp = pretraining_tp
         self.use_cache = use_cache
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling

             Beginning of stream token id.
         eos_token_id (`int`, *optional*, defaults to 2):
             End of stream token id.
         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         rope_theta (`float`, *optional*, defaults to 10000.0):
         first_k_dense_replace = 3,
         norm_topk_prob = True,
         scoring_func = 'sigmoid',
         hidden_act="silu",
         max_position_embeddings=4096,
         initializer_range=0.02,
         pad_token_id=None,
         bos_token_id=0,
         eos_token_id=1,
         tie_word_embeddings=False,
         rope_theta=10000.0,
         rope_scaling=None,
         self.first_k_dense_replace = first_k_dense_replace
         self.norm_topk_prob = norm_topk_prob
         self.scoring_func = scoring_func
         # for backward compatibility
         if num_key_value_heads is None:
             num_key_value_heads = num_attention_heads
         self.hidden_act = hidden_act
         self.initializer_range = initializer_range
         self.rms_norm_eps = rms_norm_eps
         self.use_cache = use_cache
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling

modeling_deepseek.py CHANGED Viewed

@@ -398,7 +398,6 @@ class MoEGate(nn.Module):
         self.n_routed_experts = config.n_routed_experts
         self.routed_scaling_factor = config.routed_scaling_factor
         self.scoring_func = config.scoring_func
-        self.seq_aux = config.seq_aux
         self.topk_method = config.topk_method
         self.n_group = config.n_group
         self.topk_group = config.topk_group
@@ -455,7 +454,7 @@ class MoEGate(nn.Module):
                 )
                 .reshape(bsz * seq_len, -1)
             )  # [n, e]
-            tmp_scores = scores_for_choice.masked_fill(~score_mask.bool(), 0.0)  # [n, e]
             _, topk_idx = torch.topk(
                 tmp_scores, k=self.top_k, dim=-1, sorted=False
             )

         self.n_routed_experts = config.n_routed_experts
         self.routed_scaling_factor = config.routed_scaling_factor
         self.scoring_func = config.scoring_func
         self.topk_method = config.topk_method
         self.n_group = config.n_group
         self.topk_group = config.topk_group
                 )
                 .reshape(bsz * seq_len, -1)
             )  # [n, e]
+            tmp_scores = scores_for_choice.masked_fill(~score_mask.bool(), float("-inf"))  # [n, e]
             _, topk_idx = torch.topk(
                 tmp_scores, k=self.top_k, dim=-1, sorted=False
             )