Instructions to use ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot with Transformers:

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

pipe = pipeline("text-generation", model="ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot")
model = AutoModelForCausalLM.from_pretrained("ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot")
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 ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot

SGLang

How to use ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot 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 "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot" \
    --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": "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot",
		"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 "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot" \
        --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": "ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot with Docker Model Runner:
```
docker model run hf.co/ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot
```

DeepSeek-R1-Distill-Qwen-14B — Research Reproducibility Snapshot

This repository hosts an exact, unmodified snapshot of deepseek-ai/DeepSeek-R1-Distill-Qwen-14B, preserved for research reproducibility. No weights, tokenizer files, or configurations have been altered. The snapshot was downloaded from the official DeepSeek repository on 29 April 2026 at commit 1df8507 and is uploaded here to ensure that future researchers can use the identical model artifact, even if the upstream repository is modified, versioned, or removed. This model card serves as a supplementary resource to the associated manuscript, currently under review at Information Systems Frontiers. Methodological details and results are omitted here to comply with the publication policies of the target journal and will be added upon acceptance, subject to the publisher's copyright terms.

Downloads last month: 463

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

Finetuned

(78)

this model