Update app.py

app.py

@@ -1,64 +1,59 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import os
+
+# Load the base model and tokenizer
+model_name = "mistralai/Mistral-7B-Instruct-v0.1"  # or whatever base model you used
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
 )
 
+# Load your PEFT adapter
+model = PeftModel.from_pretrained(base_model, "./model")
+
+def chat_with_model(message, history):
+    # Format the conversation
+    conversation = []
+    for human, assistant in history:
+        conversation.append(f"Human: {human}")
+        conversation.append(f"Assistant: {assistant}")
+    
+    conversation.append(f"Human: {message}")
+    conversation.append("Assistant:")
+    
+    prompt = "\n".join(conversation)
+    
+    # Tokenize and generate
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=2048)
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs.input_ids,
+            max_new_tokens=512,
+            temperature=0.7,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # Extract just the assistant's response
+    response = response.split("Assistant:")[-1].strip()
+    
+    return response
+
+# Create Gradio interface
+iface = gr.ChatInterface(
+    fn=chat_with_model,
+    title="3AI Custom Model Chat",
+    description="Chat with your custom fine-tuned Mistral model"
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()