Views
No views yet
vngrs-ai/Kumru-2B base model. Just as crows (Karga) are known for their exceptional problem-solving skills and tool use, this model has been explicitly engineered to bring Chain-of-Thought (CoT) reasoning capabilities to a 2-Billion parameter Small Language Model (SLM) for the Turkish language.<think> ... </think> block before answering, the model significantly reduces hallucinations and logically plans its outputs, making it highly effective for mathematics, logic puzzles, and code generation on Edge devices.⚠️ Academic Pre-Publication Notice This model serves as the official checkpoint for an ongoing academic research project. While the model weights are fully open-source (Apache 2.0), the proprietary synthetic dataset and the novel "Deterministic Tensor Injection Agent" training/inference architecture are temporarily withheld pending double-blind peer review. Full resources will be released upon publication.
<think> tags.1import torch
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4model_id = "ilkayO/Karga-2B-Thinking"
5tokenizer = AutoTokenizer.from_pretrained(model_id)
6model = AutoModelForCausalLM.from_pretrained(
7 model_id,
8 device_map="auto",
9 torch_dtype=torch.bfloat16
10)
11
12prompt = "Aylin'in yaşı, Burak'ın yaşının iki katıdır. Burak 12 yaşında ise, ikisinin yaşları toplamı kaçtır?"
13messages = [
14 {"role": "system", "content": "Adın Karga. Soruları mantıklı ve adım adım düşünerek yanıtla."},
15 {"role": "user", "content": prompt}
16]
17
18inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
19
20with torch.no_grad():
21 outputs = model.generate(
22 inputs,
23 max_new_tokens=1024,
24 temperature=0.6,
25 top_p=0.9,
26 repetition_penalty=1.1
27 )
28
29response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
30print(response)