Instructions to use alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B")
model = AutoModelForCausalLM.from_pretrained("alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B")
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
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B

SGLang

How to use alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B 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 "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B" \
    --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": "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B",
		"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 "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B" \
        --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": "alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B with Docker Model Runner:
```
docker model run hf.co/alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B
```

Question about the origin of alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B

by s1ngledoge - opened Feb 25

Discussion

s1ngledoge

Feb 25

Hi,

Thank you for sharing alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B.

I am looking into using this model and wanted to better understand how it relates to Qwen/Qwen2.5-Coder-0.5B before I proceed.

Could you please clarify whether alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B was built directly on top of Qwen/Qwen2.5-Coder-0.5B through a straightforward fine-tuning step, or whether there were any intermediate checkpoints, additional training rounds, merges, distillation steps, or other released models involved in between?

From a practical standpoint, I am mainly trying to understand whether it should be treated as a direct derivative of Qwen/Qwen2.5-Coder-0.5B, or as a model that has gone through extra modification stages beyond a simple direct fine-tuning path.

This would help me make better compatibility assumptions before building on top of it.

Thank you very much for your time. I would really appreciate any clarification you can provide.

Best,
Qu

alamios

Owner Feb 25

Hello,

This is a simple fine-tune of Qwen2.5-Coder-0.5B on DeepSeek-R1-Distill outputs to be used for speculative decoding, as stated in the model card.

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