File size: 787 Bytes
84bc63a f888e76 84bc63a 3f2c4d3 f888e76 1009302 1fba743 f888e76 1fba743 a0be824 f888e76 1009302 1fba743 84bc63a a7f81fe | 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 | import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model = f"tiiuae/falcon-7b"
tokenizer = AutoTokenizer.from_pretrained(model, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model,
torch_dtype=torch.bfloat16,
device_map="auto",
load_in_8bit=True,
trust_remote_code=True
)
def greet(prompt):
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
v = model.generate(
input_ids=inputs["input_ids"],
attention_mask=inputs["attention_mask"],
do_sample=True,
temperature=0.6,
top_p=0.9,
max_new_tokens=50,
)
return tokenizer.decode(v[0].to("cpu"))
iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()
|