E.g.
1text = """\
2<|im_start|>system
3당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.<|im_end|>
4<|im_start|>user
5대한민국의 수도는 어디야?<|im_end|>
6<|im_start|>assistant
7대한민국의 수도는 서울입니다.<|im_end|>
8<|im_start|>user
9서울 인구는 총 몇 명이야?<|im_end|>
10<|im_start|>assistant
11"""
This model contains the chat_template instruction format.
You can use the code below.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3device = "cuda" # the device to load the model onto
4
5model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.3")
6tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.3")
7
8messages = [
9 {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
10 {"role": "user", "content": "대한민국의 수도는 어디야?"},
11 {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
12 {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
13]
14
15encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
16
17model_inputs = encodeds.to(device)
18model.to(device)
19
20generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
21decoded = tokenizer.batch_decode(generated_ids)
22print(decoded[0])
This model is licensed under the
cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.