Instructions to use Chan-Y/TurkishReasoner-Llama3.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chan-Y/TurkishReasoner-Llama3.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="Chan-Y/TurkishReasoner-Llama3.1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Chan-Y/TurkishReasoner-Llama3.1-8B")
model = AutoModelForCausalLM.from_pretrained("Chan-Y/TurkishReasoner-Llama3.1-8B", 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 Chan-Y/TurkishReasoner-Llama3.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chan-Y/TurkishReasoner-Llama3.1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chan-Y/TurkishReasoner-Llama3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Chan-Y/TurkishReasoner-Llama3.1-8B

SGLang

How to use Chan-Y/TurkishReasoner-Llama3.1-8B 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 "Chan-Y/TurkishReasoner-Llama3.1-8B" \
    --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": "Chan-Y/TurkishReasoner-Llama3.1-8B",
		"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 "Chan-Y/TurkishReasoner-Llama3.1-8B" \
        --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": "Chan-Y/TurkishReasoner-Llama3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Chan-Y/TurkishReasoner-Llama3.1-8B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Chan-Y/TurkishReasoner-Llama3.1-8B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Chan-Y/TurkishReasoner-Llama3.1-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Chan-Y/TurkishReasoner-Llama3.1-8B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Chan-Y/TurkishReasoner-Llama3.1-8B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Chan-Y/TurkishReasoner-Llama3.1-8B with Docker Model Runner:
```
docker model run hf.co/Chan-Y/TurkishReasoner-Llama3.1-8B
```

Chan-Y commited on Apr 29, 2025

Commit

c592ed7

verified ·

1 Parent(s): 17ae242

Update README.md

Browse files

Files changed (1) hide show

README.md +48 -8

README.md CHANGED Viewed

@@ -7,17 +7,57 @@ tags:
 - llama
 - trl
 - grpo
-license: apache-2.0
 language:
-- en
 ---
-# Uploaded  model
-- **Developed by:** Chan-Y
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - llama
 - trl
 - grpo
+license: llama3.1
 language:
+- tr
 ---
+# TurkishReasoner-Llama3.1-8B
+## Model Description
+TurkishReasoner-Llama8B leverages Meta's powerful Llama3.1-8B foundation model to deliver sophisticated reasoning capabilities in Turkish. Fine-tuned using GRPO techniques, this model excels at multistep reasoning processes with particular strength in mathematical problem-solving and logical deduction.
+## Key Features
+- Built on Meta's advanced Llama3.1-8B foundation
+- Optimized for Turkish reasoning tasks with structured output
+- Balanced performance-to-resource ratio (8B parameters)
+- Strong multilingual understanding with Turkish specialization
+- Trained using Group Relative Policy Optimization (GRPO)
+- Clear step-by-step reasoning with formatted solutions
+## Technical Specifications
+- Base Model: Meta/Llama3.1-8B
+- Parameters: 8 billion
+- Input: Text
+- Hardware Requirements: ~16GB VRAM
+- Training Infrastructure: NVIDIA Ada6000 GPU
+## Usage
+This model is well-suited for a variety of Turkish reasoning applications:
+- Educational platforms requiring detailed explanations
+- Research tools analyzing complex problem-solving approaches
+- Development of Turkish-language assistants with robust reasoning
+- Applications requiring balanced performance and efficiency
+## Example Usage
+```python
+from transformers import pipeline
+pipe = pipeline("text-generation", model="Chan-Y/TurkishReasoner-Llama3.1-8B", device=0)
+messages = [
+    {"role": "system", "content": """Sen kullanıcıların isteklerine Türkçe cevap veren bir asistansın ve sana bir problem verildi.
+Problem hakkında düşün ve çalışmanı göster.
+Çalışmanı <start_working_out> ve <end_working_out> arasına yerleştir.
+Sonra, çözümünü <SOLUTION> ve </SOLUTION> arasına yerleştir.
+Lütfen SADECE Türkçe kullan."""},
+    {"role": "user", "content": "121'in karekökü kaçtır?"},
+]
+response = pipe(messages)
+print(response)
+```
+For more information or assistance with this model, please contact the developers:
+- Cihan Yalçın: https://www.linkedin.com/in/chanyalcin/
+- Şevval Nur Savcı: https://www.linkedin.com/in/%C5%9Fevval-nur-savc%C4%B1/