Tuguberk/Qwen3.5-2B-Turkish-SFT

from transformers import AutoModelForCausalLM, AutoProcessor
import torch

model_name = "Tuguberk/Qwen3.5-2B-Turkish-SFT"

processor = AutoProcessor.from_pretrained(model_name)
tokenizer = processor.tokenizer

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Sen yardımcı bir Türkçe asistansın."},
    {"role": "user",   "content": "Türkiye hakkında kısa bir bilgi verir misin?"},
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(
    inputs["input_ids"],
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9,
    do_sample=True,
)

response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)

ollama run hf.co/Tuguberk/Qwen3.5-2B-Turkish-SFT:Q4_K_M

# Metin modeli
llama-cli -hf Tuguberk/Qwen3.5-2B-Turkish-SFT --jinja

# Multimodal
llama-mtmd-cli -hf Tuguberk/Qwen3.5-2B-Turkish-SFT --jinja