Upload 2 files

app.py

@@ -42,14 +42,6 @@ import gradio as gr
 # Load the quantized model
 model = load_quantized_model("checkpoint_quantized.pt")
 
-# Set the quantization configuration for the embedding layer
-model.embed_tokens.qconfig = quantization.float_qparams_weight_only_qconfig
-
-# Apply static quantization to the rest of the model
-model.qconfig = quantization.default_qconfig
-model = quantization.prepare(model, inplace=False)
-model = quantization.convert(model, inplace=False)
-
 # Function to generate text
 def generate_text(prompt, max_length=50, temperature=1.0, top_k=50):
     input_ids = tokenizer.encode(prompt, return_tensors="pt")