Update app.py

app.py

@@ -1,62 +1,18 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
+model_name = "hari7261/TechChat"
 
-client = InferenceClient("hari7261/TechChat")
+# If the repo is private, add your token:
+token = "your_huggingface_token_here"  # or set HF_TOKEN env var
 
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=token)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=token)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+prompt = "Hello, how can I help you today?"
+inputs = tokenizer(prompt, return_tensors="pt")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_length=50)
 
-    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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))