update

app.py

@@ -50,7 +50,9 @@ base_model:
 # {model_name} (Quantized)
 
 ## Description
-This model is a quantized version of the original model `{model_name}`. It has been quantized using int4 quantization with bitsandbytes.
+This model is a quantized version of the original model [`{model_name}`](https://huggingface.co/{model_name}). 
+
+It's quantized using the BitsAndBytes library to 4-bit using the [bnb-my-repo](https://huggingface.co/spaces/HF-Quantization/bnb-my-repo) space.
 
 ## Quantization Details
 - **Quantization Type**: int4
@@ -59,12 +61,7 @@ This model is a quantized version of the original model `{model_name}`. It has b
 - **bnb_4bit_compute_dtype**: {compute_type_4}
 - **bnb_4bit_quant_storage**: {quant_storage_4}
 
-## Usage
-You can use this model in your applications by loading it directly from the Hugging Face Hub:
-```python
-from transformers import AutoModel
-
-model = AutoModel.from_pretrained("{model_name}")"""
+"""
 
     return model_card
 
@@ -153,7 +150,7 @@ def save_model(
             repo_name = f"{username}/{model_name.split('/')[-1]}-bnb-4bit"
 
         model_card = create_model_card(
-            repo_name, quant_type_4, double_quant_4, compute_type_4, quant_storage_4
+            model_name, quant_type_4, double_quant_4, compute_type_4, quant_storage_4
         )
         with open(os.path.join(tmpdirname, "README.md"), "w") as f:
             f.write(model_card)
@@ -198,30 +195,6 @@ def save_model(
     </div>
     """
 
-    code = f"""
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-
-model = AutoModelForCausalLM.from_pretrained(
-    "{repo_name}",
-    device_map="auto"
-)
-
-tokenizer = AutoTokenizer.from_pretrained("{model_name}")
-
-inputs = tokenizer("Hello, my name is", return_tensors="pt").to(model.device)
-outputs = model.generate(inputs.input_ids, max_length=50)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-"""
-    # First replace newlines in the code
-    code_html = code.replace("\n", "<br/>")
-    
-    usage_example = f"""
-    <div class="usage-example" style="margin-top: 20px; margin-bottom: 20px; background-color: #f8f9fa; padding: 15px; border-radius: 8px; border-left: 4px solid #4CAF50;">
-        <h3 style="margin-top: 0; color: #2E7D32;">📝 How to use this model</h3>
-        <div class="model-architecture" style="max-height: 500px; overflow-y: auto; overflow-x: auto; background-color: #f5f5f5; padding: 5px; border-radius: 8px; font-family: monospace; font-size: 0.75em; white-space: pre-wrap;">{code_html}</div>
-    </div>
-    """
     model_size_info = f"""
     <div class="model-size-info" style="margin-top: 20px; margin-bottom: 20px; background-color: #f8f9fa; padding: 15px; border-radius: 8px; border-left: 4px solid #4CAF50;">
         <h3 style="margin-top: 0; color: #2E7D32;">📦 Model Size</h3>
@@ -235,7 +208,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
         <p>Find your repo here: <a href="https://huggingface.co/{repo_name}" target="_blank" style="text-decoration:underline">{repo_name}</a></p>
     </div>
     """
-    return f'<h1>🎉 Quantization Completed</h1><br/>{repo_link}{model_architecture_info}{model_size_info}{usage_example}'
+    return f'<h1>🎉 Quantization Completed</h1><br/>{repo_link}{model_size_info}{model_architecture_info}'
 
 
 def quantize_and_save(