commented mixtral code

app.py

@@ -1,8 +1,8 @@
 import os
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+# import torch
 
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
@@ -20,13 +20,13 @@ qwen_client = InferenceClient(
 )
 
 # ------------------------
-# Mixtral Local Setup
+# Mixtral Local Setup (DISABLED)
 # ------------------------
-mixtral_model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-mixtral_tokenizer = AutoTokenizer.from_pretrained(mixtral_model_id)
-mixtral_model = AutoModelForCausalLM.from_pretrained(
-    mixtral_model_id, torch_dtype=torch.float16
-).to("cuda")
+# mixtral_model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+# mixtral_tokenizer = AutoTokenizer.from_pretrained(mixtral_model_id)
+# mixtral_model = AutoModelForCausalLM.from_pretrained(
+#     mixtral_model_id, torch_dtype=torch.float16
+# ).to("cuda")
 
 # ------------------------
 # Unified Inference Function with Chat History
@@ -49,21 +49,22 @@ def run_model_with_history(model_name, user_input, chat_history):
             )
             reply = result.choices[0].message.content
 
-        elif model_name == "Mixtral 8x7B":
-            full_prompt = ""
-            for msg in messages:
-                prefix = "User: " if msg["role"] == "user" else "Assistant: "
-                full_prompt += f"{prefix}{msg['content']}\n"
-            inputs = mixtral_tokenizer(full_prompt, return_tensors="pt").to("cuda")
-            outputs = mixtral_model.generate(
-                **inputs,
-                max_new_tokens=512,
-                do_sample=True,
-                temperature=0.7,
-                top_k=50,
-                top_p=0.95
-            )
-            reply = mixtral_tokenizer.decode(outputs[0], skip_special_tokens=True)
+        # Mixtral section disabled due to space constraints
+        # elif model_name == "Mixtral 8x7B":
+        #     full_prompt = ""
+        #     for msg in messages:
+        #         prefix = "User: " if msg["role"] == "user" else "Assistant: "
+        #         full_prompt += f"{prefix}{msg['content']}\n"
+        #     inputs = mixtral_tokenizer(full_prompt, return_tensors="pt").to("cuda")
+        #     outputs = mixtral_model.generate(
+        #         **inputs,
+        #         max_new_tokens=512,
+        #         do_sample=True,
+        #         temperature=0.7,
+        #         top_k=50,
+        #         top_p=0.95
+        #     )
+        #     reply = mixtral_tokenizer.decode(outputs[0], skip_special_tokens=True)
 
         else:
             reply = "❌ Invalid model selection."
@@ -90,7 +91,7 @@ with gr.Blocks() as demo:
     gr.Markdown("## 🧠 Generative AI Model Evaluation with Context")
 
     model_choice = gr.Dropdown(
-        choices=["LLaMA 4", "Qwen3 14B", "Mixtral 8x7B"],
+        choices=["LLaMA 4", "Qwen3 14B"],  # "Mixtral 8x7B" removed
         label="Select Model",
         value="LLaMA 4"
     )