Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2model_name = "neoAI/neoAI-JP-QwQ-32B"
3model = AutoModelForCausalLM.from_pretrained(
4 model_name,
5 torch_dtype="auto",
6 device_map="auto"
7)
8tokenizer = AutoTokenizer.from_pretrained(model_name)
9prompt = "How many r's are in the word \"strawberry\""
10messages = [
11 {"role": "user", "content": prompt}
12]
13text = tokenizer.apply_chat_template(
14 messages,
15 tokenize=False,
16 add_generation_prompt=True
17)
18model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
19generated_ids = model.generate(
20 **model_inputs,
21 max_new_tokens=32768
22)
23generated_ids = [
24 output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
25]
26response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
27print(response)
@misc{neoAI-JP-QwQ-32B,
title={neoAI-JP-QwQ-32B},
url={https://huggingface.co/neoai-inc/neoAI-JP-QwQ-32B},
author={Gouki Minegishi and Kai Yamashita and Koki Itai and Masaki Otsuki and Toshiki Kawamoto},
year={2025},
}