Update app.py

app.py

@@ -11,7 +11,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 DESCRIPTION = '''
 <div>
-<h1 style="text-align: center;">deepseek-ai/DeepSeek-R1-Distill-Llama-8B</h1>
+<h1 style="text-align: center;">DeepSeek-R1-Zero</h1>
 </div>
 '''
 
@@ -44,8 +44,8 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B")
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B", device_map="auto")  # to("cuda:0") 
+tokenizer = AutoTokenizer.from_pretrained("reedmayhew/DeepSeek-R1-Refined-Llama-3.1-8B-hf")
+model = AutoModelForCausalLM.from_pretrained("reedmayhew/DeepSeek-R1-Refined-Llama-3.1-8B-hf", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")
@@ -110,15 +110,15 @@ with gr.Blocks(fill_height=True, css=css) as demo:
         fill_height=True,
         additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
         additional_inputs=[
-            gr.Slider(minimum=0,
-                      maximum=1, 
+            gr.Slider(minimum=0.6,
+                      maximum=0.6, 
                       step=0.1,
-                      value=0.5, 
+                      value=0.6, 
                       label="Temperature", 
                       render=False),
             gr.Slider(minimum=128, 
                       maximum=4096,
-                      step=1,
+                      step=64,
                       value=1024, 
                       label="Max new tokens", 
                       render=False ),