File size: 769 Bytes
9c31c2b
 
06f1120
 
 
 
9c31c2b
 
 
 
 
 
 
 
 
 
29f61ed
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from huggingface_hub import login
token1="hf_"
token2="rPlNHzkJScHYmtGSaQPcaoKcjJGYQEpjLu"
login(token=token1+token2)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")

def get_response(prompt, max_new_tokens=50):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=0.0001, do_sample=True)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)  # Use indexing instead of calling
    ans=response.toString()
    return ans