File size: 1,852 Bytes
05cc5b6 5a4cfee 2cecba6 05cc5b6 5a4cfee 95cd9f3 5a4cfee 2cecba6 5a4cfee f7ebb72 5a4cfee 95cd9f3 5a4cfee 0b415e2 |
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 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# Modeli yükleyin
model_name = "bkaplan/MRL1"
try:
# Tokenizer ve modeli yükleme
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
def respond(message, history, system_message, max_tokens, temperature, top_p):
try:
# Girdiyi hazırlama
input_text = f"System: {system_message}\nUser: {message}\nAssistant:"
# Tokenize etme
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
# Üretim parametreleri
outputs = model.generate(
**inputs,
max_length=max_tokens,
temperature=temperature,
top_p=top_p,
num_return_sequences=1,
do_sample=True
)
# Yanıtı çözme
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
yield response
except Exception as e:
yield f"Hata oluştu: {str(e)}"
# Gradio arayüzü
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
]
)
if __name__ == "__main__":
demo.launch(share=True)
except Exception as e:
print(f"Model yüklenirken hata oluştue: {e}") |