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

Libraries

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

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V2", 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-V2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V2", 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 deepseek-ai/DeepSeek-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V2"
# 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-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

training: fix type mismatch when training

by Jack477 - opened May 27, 2024

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

-0

Jack477

May 27, 2024

No description provided.

convert moe results to input dtype827ce49e

Jack477 changed pull request status to open May 27, 2024

Jack477 changed pull request title from fix type mismatch when training to training: fix type mismatch when training May 27, 2024

Jack477

May 27, 2024

error stack when using fp16 training :

  File "/root/.cache/huggingface/modules/transformers_modules/modeling_deepseek.py", line 1252, in forward
    hidden_states, self_attn_weights, present_key_value = self.self_attn(
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1570, in _call_impl
    result = forward_call(*args, **kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/modeling_deepseek.py", line 821, in forward
    q = self.q_proj(hidden_states)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1570, in _call_impl
    result = forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
  File "/usr/local/lib/python3.8/dist-packages/deepspeed/runtime/zero/linear.py", line 109, in zero3_linear_wrap
    return LinearFunctionForZeroStage3.apply(input, weight)
  File "/usr/local/lib/python3.8/dist-packages/torch/autograd/function.py", line 506, in apply
    return super().apply(*args, **kwargs)  # type: ignore[misc]
  File "/usr/local/lib/python3.8/dist-packages/torch/cuda/amp/autocast_mode.py", line 98, in decorate_fwd
    return fwd(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/deepspeed/runtime/zero/linear.py", line 57, in forward
    output = input.matmul(weight.t())
RuntimeError: expected scalar type Float but found Half

luofuli changed pull request status to merged May 27, 2024

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