Model Card for khazarai/AzQwen

Model Details

This model is a fine-tuned version of unsloth/Qwen3-1.7B on a translated version of the Alpaca Stanford dataset in Azerbaijani language. The model is instruction-tuned to better follow prompts and generate relevant responses in Azerbaijani.

Model Description

Language(s) (NLP): Azerbaijani
License: MIT
Finetuned from model: unsloth/Qwen3-1.7B

Uses

Direct Use

Instruction following in Azerbaijani
Education, research, and experimentation with low-resource language LLMs
Chatbots, task-oriented systems, language agents

How to Get Started with the Model

Use the code below to get started with the model.

from huggingface_hub import login
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel


tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B",)
base_model = AutoModelForCausalLM.from_pretrained(
    "unsloth/Qwen3-1.7B",
    device_map={"": 0}
)

model = PeftModel.from_pretrained(base_model,"khazarai/AzQwen")


question = "Bir sifət əlavə edərək aşağıdakı cümləni yenidən yazın. Tələbə mürəkkəb anlayışları anlaya bildi. "

messages = [
    {"role" : "user", "content" : question}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize = False,
    add_generation_prompt = True, 
    enable_thinking = False, 
)

from transformers import TextStreamer
_ = model.generate(
    **tokenizer(text, return_tensors = "pt").to("cuda"),
    max_new_tokens = 2048,
    temperature = 0.7, 
    top_p = 0.8, 
    top_k = 20,
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)

For pipeline:

from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B")
base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-1.7B")
model = PeftModel.from_pretrained(base_model, "khazarai/AzQwen")

question ="""
Bir sifət əlavə edərək aşağıdakı cümləni yenidən yazın. Tələbə mürəkkəb anlayışları anlaya bildi. 
"""

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
messages = [
    {"role": "user", "content": question}
]
pipe(messages)