Update app.py

app.py

@@ -1,69 +1,51 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-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 = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        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(
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE = "microsoft/phi-3-mini-4k-instruct"
+ADAPTER = "Znilsson/survivalai-phi3-lora"
+TOKEN = os.environ.get("HF_TOKEN")
+
+print("Loading base model (first load ~3 min)...")
+tokenizer = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    BASE, torch_dtype=torch.float32, trust_remote_code=True, low_cpu_mem_usage=True
+)
+print("Attaching LoRA adapter...")
+model = PeftModel.from_pretrained(model, ADAPTER, token=TOKEN)
+model = model.merge_and_unload()
+model.eval()
+print("Ready.")
+
+def respond(message, history):
+    msgs = [{"role": "user", "content": message}]
+    inputs = tokenizer.apply_chat_template(
+        msgs, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+    )
+    with torch.no_grad():
+        out = model.generate(
+            inputs,
+            max_new_tokens=400,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.1,
+        )
+    response = tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True)
+    return response
+
+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)",
-        ),
+    title="SurvivalAI — Phi-3 LoRA demo",
+    description="Fine-tuned on ~150k survival/preparedness QA pairs. Slow on free CPU (~20s/response).",
+    examples=[
+        "How do I purify water from a stream with nothing but a pot?",
+        "My friend is hypothermic. What do I do?",
+        "List three edible wild plants in temperate forests.",
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
     demo.launch()