Update app.py

app.py

@@ -1,21 +1,19 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from huggingface_hub import InferenceClient
 
 model_id = "yuvrajpant56/Mistral_Posttrain_SFT"
-
-# Load model & tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+client = InferenceClient(model_id)
 
 def generate_text(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(**inputs, max_new_tokens=100)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = ""
+    for token in client.text_generation(prompt, stream=True, max_new_tokens=100):
+        response += token.token
+    return response
 
-gr.Interface(fn=generate_text,
-             inputs="text",
-             outputs="text",
-             title="Mistral SFT Text Generator",
-             description="Type a prompt and let the fine-tuned Mistral model generate the rest."
+gr.Interface(
+    fn=generate_text,
+    inputs="text",
+    outputs="text",
+    title="Mistral SFT Text Generator",
+    description="Type a prompt and let the fine-tuned Mistral model generate the rest."
 ).launch()