Instructions to use deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", 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-Coder-V2-Lite-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", 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 deepseek-ai/DeepSeek-Coder-V2-Lite-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-V2-Lite-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-V2-Lite-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

SGLang

How to use deepseek-ai/DeepSeek-Coder-V2-Lite-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-V2-Lite-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-V2-Lite-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-V2-Lite-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-V2-Lite-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
```

mashirong commited on Jun 24, 2024

Commit

45d0aa4

1 Parent(s): ec228ab

Update modeling_deepseek.py

Browse files

Files changed (1) hide show

modeling_deepseek.py +9 -3

modeling_deepseek.py CHANGED Viewed

@@ -552,7 +552,9 @@ class DeepseekV2MoE(nn.Module):
             self.ep_rank = 0
             self.experts = nn.ModuleList(
                 [
-                    DeepseekV2MLP(config, intermediate_size=config.moe_intermediate_size)
                     for i in range(config.n_routed_experts)
                 ]
             )
@@ -577,7 +579,7 @@ class DeepseekV2MoE(nn.Module):
             for i, expert in enumerate(self.experts):
                 y[flat_topk_idx == i] = expert(hidden_states[flat_topk_idx == i])
             y = (y.view(*topk_weight.shape, -1) * topk_weight.unsqueeze(-1)).sum(dim=1)
-            y = y.view(*orig_shape)
             y = AddAuxiliaryLoss.apply(y, aux_loss)
         else:
             y = self.moe_infer(hidden_states, topk_idx, topk_weight).view(*orig_shape)
@@ -1023,7 +1025,11 @@ class DeepseekV2FlashAttention2(DeepseekV2Attention):
             elif torch.is_autocast_enabled():
                 target_dtype = torch.get_autocast_gpu_dtype()
             else:
-                target_dtype = self.q_proj.weight.dtype if self.q_lora_rank is None else self.q_a_proj.weight.dtype
             logger.warning_once(
                 f"The input hidden states seems to be silently casted in float32, this might be related to"

             self.ep_rank = 0
             self.experts = nn.ModuleList(
                 [
+                    DeepseekV2MLP(
+                        config, intermediate_size=config.moe_intermediate_size
+                    )
                     for i in range(config.n_routed_experts)
                 ]
             )
             for i, expert in enumerate(self.experts):
                 y[flat_topk_idx == i] = expert(hidden_states[flat_topk_idx == i])
             y = (y.view(*topk_weight.shape, -1) * topk_weight.unsqueeze(-1)).sum(dim=1)
+            y = y.to(hidden_states.dtype).view(*orig_shape)
             y = AddAuxiliaryLoss.apply(y, aux_loss)
         else:
             y = self.moe_infer(hidden_states, topk_idx, topk_weight).view(*orig_shape)
             elif torch.is_autocast_enabled():
                 target_dtype = torch.get_autocast_gpu_dtype()
             else:
+                target_dtype = (
+                    self.q_proj.weight.dtype
+                    if self.q_lora_rank is None
+                    else self.q_a_proj.weight.dtype
+                )
             logger.warning_once(
                 f"The input hidden states seems to be silently casted in float32, this might be related to"