File size: 1,421 Bytes
87a26ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import os
# PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'expandable_segments:True'
torch.random.manual_seed(0)
model = AutoModelForCausalLM.from_pretrained(
"NyxKrage/Microsoft_Phi-4",
device_map="cuda",
torch_dtype="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("NyxKrage/Microsoft_Phi-4")
messages = [
{"role": "system", "content": "You are a helpful AI assistant."},
{"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
{"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
{"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"return_full_text": False,
"temperature": 0.0,
"do_sample": False,
}
@spaces.GPU
def tuili():
output = pipe(messages, **generation_args)
return output
print(tuili()[0]['generated_text'])
|