Instructions to use complingkarakas/turkish-gpt2_tree_of_thought with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use complingkarakas/turkish-gpt2_tree_of_thought with Transformers:

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

pipe = pipeline("text-generation", model="complingkarakas/turkish-gpt2_tree_of_thought")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("complingkarakas/turkish-gpt2_tree_of_thought")
model = AutoModelForCausalLM.from_pretrained("complingkarakas/turkish-gpt2_tree_of_thought", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use complingkarakas/turkish-gpt2_tree_of_thought with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "complingkarakas/turkish-gpt2_tree_of_thought"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "complingkarakas/turkish-gpt2_tree_of_thought",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/complingkarakas/turkish-gpt2_tree_of_thought

SGLang

How to use complingkarakas/turkish-gpt2_tree_of_thought 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 "complingkarakas/turkish-gpt2_tree_of_thought" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "complingkarakas/turkish-gpt2_tree_of_thought",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "complingkarakas/turkish-gpt2_tree_of_thought" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "complingkarakas/turkish-gpt2_tree_of_thought",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use complingkarakas/turkish-gpt2_tree_of_thought with Docker Model Runner:
```
docker model run hf.co/complingkarakas/turkish-gpt2_tree_of_thought
```

turkish-gpt2_tree_of_thought

This model is a fine-tuned version of cenkersisman/gpt2-turkish-10m on the None dataset.

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: 3e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 3

Training results

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1

🔰 How to get started

You can start generating Turkish chain-of-thought answers with one line of transformers code or a simple curl call.

1. Python / Transformers

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="complingkarakas/turkish-gpt2_tree_of_thought",
    device=0          # -1 → CPU, 0 → first GPU
)

prompt = (
    "Soru: \n"
    "Adım adım düşünerek yanıt ver:\n"
)

out = pipe(
    prompt,
    max_new_tokens=200,
    do_sample=False,          # deterministic; set True + temperature for creativity
    eos_token_id=pipe.tokenizer.eos_token_id
)[0]["generated_text"]

print(out)

Downloads last month: 23

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for complingkarakas/turkish-gpt2_tree_of_thought

Base model

cenkersisman/gpt2-turkish-10m

Finetuned

(1)

this model