Fetching metadata from the HF Docker repository...
-
Update app.py
-
Update app.py
-
Update app.py
-
Update app.py
-
Create requirements.txt
-
Update app.py
-
Create app.py
-
Delete app.py
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "你的模型路径"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16
).to("cuda")
def chat(user_input):
inputs = tokenizer(user_input, return_tensors="pt").to("cuda")
outputs = model.generate(
**inputs,
max_new_tokens=200,
temperature=0.7,
top_p=0.9
)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
interface = gr.Interface(
fn=chat,
inputs=gr.Textbox(lines=3, label="输入你的问题"),
outputs=gr.Textbox(lines=6, label="模型回答"),
title="你自己的AI模型",
description="这是一个你训练的 LLaMA/GPT 的网页版本"
)
interface.launch() -
Create app.py
-
initial commit
