Update app.py

app.py

@@ -2,17 +2,27 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "imsuprtwo2/NanoBit-300M"
+model_id = "imsuprtwo2/FastBit-450M-DeepCoder"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    weight_files=["nanorons.safetensors"], 
+    dtype=torch.float32,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True  
+)
 
-def predict(message, history):
+def chat_response(message, history):
     inputs = tokenizer(message, return_tensors="pt")
     with torch.no_grad():
-        outputs = model.generate(**inputs, max_new_tokens=100, do_sample=True, temperature=0.7)
+        outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.8)
     
-    full_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return full_text[len(message):].strip()
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response[len(message):].strip()
 
-gr.ChatInterface(predict).launch()
+gr.ChatInterface(
+    chat_response, 
+    title="FastBit-450M DeepCoder",
+    description="The official project coding assistant."
+).launch()