tt

app.py

@@ -2,17 +2,22 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 
-# Load model and tokenizer
+# Load model and tokenizer with trust_remote_code=True
 model_id = "PowerInfer/SmallThinker-21BA3B-Instruct"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(
+    model_id,
+    trust_remote_code=True  # Required for models with custom code
+)
+
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    device_map="cpu",  # Force CPU
-    torch_dtype=torch.float32
+    device_map="cpu",              # Run on CPU
+    torch_dtype=torch.float32,     # Use float32 on CPU
+    trust_remote_code=True         # Allow custom code execution
 )
 
-# Create generation pipeline
+# Create text generation pipeline
 generator = pipeline(
     "text-generation",
     model=model,
@@ -20,7 +25,7 @@ generator = pipeline(
     device=-1  # CPU
 )
 
-# Inference function
+# Define the chat function
 def chat(prompt, max_new_tokens=256, temperature=0.7):
     output = generator(
         prompt,
@@ -31,7 +36,7 @@ def chat(prompt, max_new_tokens=256, temperature=0.7):
     )
     return output[0]["generated_text"]
 
-# Launch Gradio app
+# Launch the Gradio interface
 gr.Interface(
     fn=chat,
     inputs=[