Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
Sungur-9B is a Turkish-specialized large language model derived from ytu-ce-cosmos/Turkish-Gemma-9b-v0.1, which itself is based on Gemma-2-9b. The model was further trained using a 7k-sample Direct Preference Optimization (DPO) dataset created via translation and fine-tuned with 4-bit QLoRA, refining its alignment with human preferences.
Sungur-9B is designed for Turkish text generation tasks, producing coherent and contextually appropriate outputs. Its training process enables it to deliver fluent, context-aware responses.
from transformers import pipeline
pipe = pipeline("text-generation", model="suayptalha/Sungur-9B")
messages = [
{"role": "user", "content": "Bana kuantum dolanıklığını çok kısaca anlat."},
]
pipe(messages)[0]["generated_text"][-1]["content"]
#Kuantum dolanıklığı, birbirine bağlı iki parçacığın, ne kadar uzakta olsalar bile, birinin durumunun diğerini anında etkilemesi olarak düşünülebilir.#Örneğin, bir parçacık "yukarı" döndüğünde, dolanık olduğu diğer parçacık kesinlikle "aşağı" dönecektir. Bu değişim anında gerçekleşir, ışık hızını aşarak. Fakat bu durum, uzaktaki parçacığın bir "bilgiyi" aldığını göstermez, çünkü ölçüm sonucu zaten önceden belirlenmiştir.#Dolanıklık, kuantum dünyasının tuhaf ve ilginç bir özelliğidir ve bilgi teknolojileri (kuantum bilgisayarlar) gibi alanlarda devrim yaratma potansiyeline sahiptir.
AutoModelForCausalLM
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "suayptalha/Sungur-9B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "user", "content": "5x + 1 = 16. x'i bul."},
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=2048,
do_sample=False,
eos_token_id=tokenizer.eos_token_id
)
output_ids = outputs[0]
input_length = inputs["input_ids"].shape[1]
generated_tokens = output_ids[input_length:]
answer = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(answer)
# 5x + 1 = 16 denklemini çözmek için şu adımları izleyelim:# 1. **Sabit terimi eşitliğin diğer tarafına taşıyalım:**# 5x = 16 - 1# 5x = 15# 2. **x'i yalnız bırakmak için her iki tarafı 5'e bölelim:**# x = 15 / 5# x = 3# **Sonuç:** x = 3# Denklemi kontrol edelim:# 5 * 3 + 1 = 15 + 1 = 16 (Doğru)
Acknowledgments
Thanks to
ytu-ce-cosmos
for their amazing Turkish-Gemma-9b-v0.1 model.
Thanks to
axolotl
for making the repository I used to make this model.
Thanks to all Turkish open source AI community.
Citation
@misc{sungur_collection_2025,
title = {Sungur (Hugging Face Collection)},
author = {Şuayp Talha Kocabay},
year = {2025},
howpublished = {\url{https://huggingface.co/collections/suayptalha/sungur-68dcd094da7f8976cdc5898e}},
note = {Turkish LLM family and dataset collection}
}
Support
license: gemma2
Runs of suayptalha Sungur-9B on huggingface.co
31
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Sungur-9B huggingface.co Model
Sungur-9B huggingface.co is an AI model on huggingface.co that provides Sungur-9B's model effect (), which can be used instantly with this suayptalha Sungur-9B model. huggingface.co supports a free trial of the Sungur-9B model, and also provides paid use of the Sungur-9B. Support call Sungur-9B model through api, including Node.js, Python, http.
Sungur-9B huggingface.co is an online trial and call api platform, which integrates Sungur-9B's modeling effects, including api services, and provides a free online trial of Sungur-9B, you can try Sungur-9B online for free by clicking the link below.
suayptalha Sungur-9B online free url in huggingface.co:
Sungur-9B is an open source model from GitHub that offers a free installation service, and any user can find Sungur-9B on GitHub to install. At the same time, huggingface.co provides the effect of Sungur-9B install, users can directly use Sungur-9B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.