Instructions to use Tandogan/sft_finetuned_big with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tandogan/sft_finetuned_big with Transformers:

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

pipe = pipeline("text-generation", model="Tandogan/sft_finetuned_big")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tandogan/sft_finetuned_big")
model = AutoModelForCausalLM.from_pretrained("Tandogan/sft_finetuned_big")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tandogan/sft_finetuned_big with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tandogan/sft_finetuned_big

SGLang

How to use Tandogan/sft_finetuned_big 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 "Tandogan/sft_finetuned_big" \
    --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": "Tandogan/sft_finetuned_big",
		"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 "Tandogan/sft_finetuned_big" \
        --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": "Tandogan/sft_finetuned_big",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tandogan/sft_finetuned_big with Docker Model Runner:
```
docker model run hf.co/Tandogan/sft_finetuned_big
```

Model Card for Model ID

This repository hosts a supervised fine-tuned (SFT) version of the Qwen/Qwen3-0.6B-Base language model, trained on the Tandogan/sft_dataset_big dataset.

Model Details

Model name: Qwen/Qwen3-0.6B-Base
Fine-tuned on: Tandogan/sft_dataset_big

Intended Uses

Primary use case: Tasks requiring generation of human-like text in domains covered by the fine-tuning dataset.
Examples: Question answering, text summarization, code completion, conversational agents.
Not suitable for: Safety-critical applications, generating legal or medical advice without human oversight.

How to Use

You can use the model with the transformers and trl libraries for inference or evaluation:

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("Tandogan/sft_finetuned_big").to("cuda")
tokenizer = AutoTokenizer.from_pretrained("Tandogan/sft_finetuned_big")

prompt = "Explain recursion in simple terms."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 4

Safetensors

Model size

0.6B params

Tensor type

BF16