File size: 685 Bytes
22cf642
 
 
 
564bd7c
 
22cf642
 
 
 
 
 
5f6d4f4
22cf642
 
5525b46
22cf642
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "NousResearch/Hermes-2-Pro-Llama-3-8B"

model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Example messages input
# messages = [
# {"role": "system", "content": "You are Hermes 2."},
# {"role": "user", "content": "Hello, who are you?"}
#]
  
def generate(messages):
  gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
  output_ids = model.generate(**gen_input, num_beams=3, no_repeat_ngram_size=2, max_new_tokens=100, eos_token_id=tokenizer.eos_token_id)
  
  return tokenizer.decode(output_ids[0], skip_special_tokens=True)