Instructions to use suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0 with Transformers:

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

pipe = pipeline("text-generation", model="suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0")
model = AutoModelForCausalLM.from_pretrained("suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0

SGLang

How to use suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0 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 "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0" \
    --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": "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0",
		"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 "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0" \
        --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": "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0 with Docker Model Runner:
```
docker model run hf.co/suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0
```

A newer version of this model is available: suayptalha/DeepSeek-R1-Distill-Llama-3B

DeepSeek-R1-Distill-Llama-3B

This model is the distilled version of DeepSeek-R1 on Llama-3.2-3B with R1-Distill-SFT dataset. This model is 4bit quantized! You should import it f16 if you want to use full model.

Example usage:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit",
    load_in_4bit = True,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained("suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit")

SYSTEM_PROMPT = """Respond in the following format:
<reasoning>
You should reason between these tags.
</reasoning>

Answer goes here...

Always use <reasoning> </reasoning> tags even if they are not necessary.
"""

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": "Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True,
    return_tensors = "pt",
).to("cuda")
output = model.generate(input_ids=inputs, max_new_tokens=256, use_cache=True, temperature=0.7)
decoded_output = tokenizer.decode(output[0], skip_special_tokens=False)
print(decoded_output)

Output:

<reasoning>
To continue the Fibonacci sequence, we need to recall the pattern of adding the previous two numbers to get the next number.
</reasoning>

The next numbers in the sequence would be: 13, 21, 34, 55, 89, 144

Suggested system prompt:

Respond in the following format:
<reasoning>
You should reason between these tags.
</reasoning>

Answer goes here...

Always use <reasoning> </reasoning> tags even if they are not necessary.

Parameters

lr: 2e-5
epochs: 1
optimizer: paged_adamw_8bit

Support

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

F32

F16

Model tree for suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(500)

this model

suayptalha
/

DeepSeek-R1-Distill-Llama-3B-4bit-v0

DeepSeek-R1-Distill-Llama-3B

Parameters

Support

Model tree for suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0

Dataset used to train suayptalha/DeepSeek-R1-Distill-Llama-3B-4bit-v0