Instructions to use deepseek-ai/deepseek-math-7b-rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-math-7b-rl with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-math-7b-rl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-math-7b-rl")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-math-7b-rl", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/deepseek-math-7b-rl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-math-7b-rl"
# 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-math-7b-rl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-math-7b-rl

SGLang

How to use deepseek-ai/deepseek-math-7b-rl 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-math-7b-rl" \
    --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-math-7b-rl",
		"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-math-7b-rl" \
        --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-math-7b-rl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-math-7b-rl with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-math-7b-rl
```

ZhihongShao commited on Feb 25, 2024

Commit

d16cb8a

verified ·

1 Parent(s): dafda4a

Add cot instruction

Browse files

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -28,19 +28,24 @@ Here give some examples of how to use our model.
 **Chat Completion**
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
-model_name = "deepseek-ai/deepseek-math-7b-rl"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
 model.generation_config = GenerationConfig.from_pretrained(model_name)
 model.generation_config.pad_token_id = model.generation_config.eos_token_id
 messages = [
-    {"role": "user", "content": "what is the integral of x^2 from 0 to 2?"}
 ]
 input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

 **Chat Completion**
+❗❗❗ **Please use chain-of-thought prompt to test DeepSeekMath-Instruct and DeepSeekMath-RL:**
+- English questions: **{question}\nPlease reason step by step, and put your final answer within \\boxed{}.**
+- Chinese questions: **{question}\n请通过逐步推理来解答问题，并把最终答案放置于\\boxed{}中。**
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+model_name = "deepseek-ai/deepseek-math-7b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
 model.generation_config = GenerationConfig.from_pretrained(model_name)
 model.generation_config.pad_token_id = model.generation_config.eos_token_id
 messages = [
+    {"role": "user", "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}."}
 ]
 input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)