malhajar/arc-tr
Viewer • Updated • 7.78k • 374 • 8
How to use uisikdag/qwen3-14b-arc-tr with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("uisikdag/qwen3-14b-arc-tr", device_map="auto")This model is a fine-tuned version of unsloth/Qwen3-14B-unsloth-bnb-4bit. It has been trained using TRL.
from unsloth import FastLanguageModel
from unsloth.chat_templates import get_chat_template
# Load model
model, tokenizer = FastLanguageModel.from_pretrained(
"uisikdag/qwen3-14b-arc-tr",
max_seq_length=2048,
load_in_4bit=True,
)
tokenizer = get_chat_template(tokenizer, chat_template="qwen2.5")
FastLanguageModel.for_inference(model)
# Predict
question = "Fotosentez sırasında bitkiler hangi gazı üretir?"
options = ["A Karbondioksit", "B Oksijen", "C Azot", "D Hidrojen"]
prompt = f"Soru: {question}\n\nSecenekler:\n" + "\n".join(options) + "\n\nDogru cevap hangisi?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids=inputs, max_new_tokens=64, temperature=0.1)
response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("assistant")[-1].strip()
print(f"Cevap: {response}")
This model was trained with SFT.
Cite TRL as:
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
Base model
Qwen/Qwen3-14B-Base