File size: 598 Bytes
3cc5fba
 
 
30a4c4a
3cc5fba
 
d62d1f9
3cc5fba
 
 
 
 
 
 
 
30a4c4a
3cc5fba
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralBeagle14-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])