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

Libraries

How to use duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish with Transformers:

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

pipe = pipeline("text-generation", model="duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish")
model = AutoModelForCausalLM.from_pretrained("duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish")
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 duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish

SGLang

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

Docker Model Runner
How to use duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish with Docker Model Runner:
```
docker model run hf.co/duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DeepSeek-R1-Distill-Qwen-1.5B-Turkish

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the reasoning-turkish-R1 dataset. It achieves the following results on the evaluation set:

Loss: 1.1396

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.6161	0.1028	26	1.4920
1.3683	0.2055	52	1.3256
1.409	0.3083	78	1.2486
1.1914	0.4111	104	1.2049
1.1264	0.5138	130	1.1763
1.1721	0.6166	156	1.1584
1.2738	0.7194	182	1.1467
1.1729	0.8221	208	1.1415
1.4446	0.9249	234	1.1399

Framework versions

Transformers 4.48.2
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 3

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for duxx/DeepSeek-R1-Distill-Qwen-1.5B-Turkish

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Finetuned

(632)

this model

Adapters

4 models

Quantizations

1 model