Update space

app.py

@@ -1,70 +1,72 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
 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(
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+# -------------------------
+# Base + Adapter configuration
+# -------------------------
+
+base_model_name = "Qwen/Qwen3-4B-Instruct-2507"
+adapter_model_name = "help2opensource/Qwen3-4B-Instruct-2507_mental_health_therapy"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# -------------------------
+# Load base model and tokenizer
+# -------------------------
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.float16 if device == "cuda" else torch.float32,
+).to(device)
+
+# -------------------------
+# Load LoRA adapter
+# -------------------------
+model = PeftModel.from_pretrained(base_model, adapter_model_name)
+
+# Optional: merge LoRA weights for faster inference
+model = model.merge_and_unload()
+
+
+def predict(message, history):
+    # Ensure history format is consistent
+    messages = history + [{"role": "user", "content": message}]
+
+    # Apply chat template correctly
+    try:
+        input_text = tokenizer.apply_chat_template(
+            messages, tokenize=False, add_generation_prompt=True
+        )
+    except TypeError:
+        # For older tokenizers that don't support add_generation_prompt
+        input_text = tokenizer.apply_chat_template(messages, tokenize=False)
+
+    inputs = tokenizer(input_text, return_tensors="pt").to(device)
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=1024,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True,
+        )
+
+    decoded = tokenizer.decode(outputs[0], skip_special_tokens=False)
+
+    # Extract only the assistant’s final response
+    if "<|im_start|>assistant" in decoded:
+        response = (
+            decoded.split("<|im_start|>assistant")[-1].split("<|im_end|>")[0].strip()
+        )
+    else:
+        response = decoded
+
+    return response
+
+
+demo = gr.ChatInterface(predict, type="messages")
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers>=4.42.0
+torch>=2.1.0
+accelerate>=0.29.0
+peft>=0.10.0
+bitsandbytes>=0.42.0
+gradio>=4.0