Instructions to use ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain with Transformers:

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

pipe = pipeline("text-generation", model="ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain")
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("ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain")
model = AutoModelForCausalLM.from_pretrained("ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain", 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 ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain

SGLang

How to use ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain 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 "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain" \
    --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": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain",
		"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 "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain" \
        --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": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain with Docker Model Runner:
```
docker model run hf.co/ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain
```

OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain / training_metadata.json

dd101bb

Release verified OPTD checkpoint

12485f3 verified 6 days ago

Raw History Blame Contribute Delete

272 Bytes

{
  "repo_id": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain",
  "base_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
  "step": 150,
  "layers": [
    11,
    15,
    19
  ],
  "domains": [
    "math",
    "coding",
    "instruction-following"
  ]
}

	{
	"repo_id": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain",
	"base_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
	"step": 150,
	"layers": [
	11,
	15,
	19
	],
	"domains": [
	"math",
	"coding",
	"instruction-following"
	]
	}