Views
No views yet
Oganesson-TinyLlama-1.2B is a lightweight and efficient language model built on the LLaMA 3.2 1.2B architecture. Fine-tuned for general-purpose inference, mathematical reasoning, and code generation, it’s ideal for edge devices, personal assistants, and educational applications requiring a compact yet capable model.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_name = "prithivMLmods/Oganesson-TinyLlama-1.2B"
4
5model = AutoModelForCausalLM.from_pretrained(
6 model_name,
7 torch_dtype="auto",
8 device_map="auto"
9)
10tokenizer = AutoTokenizer.from_pretrained(model_name)
11
12prompt = "Write a Python function to compute the Fibonacci sequence."
13
14messages = [
15 {"role": "system", "content": "You are a helpful coding and math assistant."},
16 {"role": "user", "content": prompt}
17]
18
19text = tokenizer.apply_chat_template(
20 messages,
21 tokenize=False,
22 add_generation_prompt=True
23)
24
25model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
26
27generated_ids = model.generate(
28 **model_inputs,
29 max_new_tokens=512
30)
31generated_ids = [
32 output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
33]
34
35response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
36print(response)