local_model_update

app.py

@@ -1,64 +1,66 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+model_id = "distilgpt2"  # small enough to run locally on CPU
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
-    messages = [{"role": "system", "content": system_message}]
 
-    messages.extend(history)
+def chat(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=100,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+# def respond(
+#     message,
+#     history: list[dict[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+#     hf_token: gr.OAuthToken,
+# ):
+#     """
+#     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(token=hf_token.token, model="openai/gpt-oss-20b")
 
-    messages.append({"role": "user", "content": message})
+#     messages = [{"role": "system", "content": system_message}]
 
-    response = ""
+#     messages.extend(history)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+#     messages.append({"role": "user", "content": message})
 
-        response += token
-        yield response
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         choices = message.choices
+#         token = ""
+#         if len(choices) and choices[0].delta.content:
+#             token = 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
 """
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
+chatbot = gr.Interface(fn=chat, inputs="text", outputs="text", title="Local HF Model Chatbot")
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
@@ -68,3 +70,4 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     demo.launch()
+