Spaces:
Runtime error
Runtime error
File size: 2,549 Bytes
867ef01 392dfeb 867ef01 392dfeb 867ef01 392dfeb 867ef01 392dfeb 867ef01 392dfeb 867ef01 392dfeb 867ef01 |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
from fastapi import FastAPI
import time
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cpu" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2-0.5B-Instruct",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
app = FastAPI()
@app.get("/")
async def read_root():
return {"Hello": "World!"}
start_time = time.time()
messages = [
{"role": "system", "content": "You are a helpful assistant, Sia. You are developed by Sushma. You will response in polity and brief."},
{"role": "user", "content": "Who are you?"},
{"role": "assistant", "content": "I am Sia, a small language model created by Sushma. I am here to assist you."},
{"role": "user", "content": "Hi, How are you?"}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=64
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
end_time = time.time()
time_taken = end_time - start_time
print(time_taken)
@app.get("/test")
async def read_droot():
starttime = time.time()
messages = [
{"role": "system", "content": "You are a helpful assistant, Sia. You are developed by Sushma. You will response in polity and brief."},
{"role": "user", "content": "Who are you?"},
{"role": "assistant", "content": "I am Sia, a small language model created by Sushma. I am here to assist you."},
{"role": "user", "content": "Hi, How are you?"}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=64
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
end_time = time.time()
time_taken = end_time - starttime
print(time_taken)
return {"Hello": "World!"} |