Upload 3 files

README.md

@@ -1,13 +1,14 @@
----
-title: Medical Chatbot Using OpenbioLLM
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: other
----
+# 🧬 OpenBioLLM Chatbot on Hugging Face
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+This Space uses [OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B), a biomedical large language model based on Llama 3, to answer medical and life science-related questions interactively using Gradio.
+
+## 🚀 Features
+- Biomedical-aware chatbot
+- Powered by Hugging Face Transformers
+- Runs in a Gradio ChatInterface
+
+## 🛠 How to Use
+1. Clone this Space
+2. Add `app.py` and `requirements.txt`
+3. Select a GPU runtime (free or Pro)
+4. Chat away!

app.py

@@ -1,64 +1,21 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
 
-"""
-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")
+model_id = "aaditya/Llama3-OpenBioLLM-8B"
 
-
-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)",
-        ),
-    ],
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.float16
 )
 
+chat_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def chatbot(message, history=[]):
+    prompt = f"[INST] {message} [/INST]"
+    response = chat_pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)[0]['generated_text']
+    return response.replace(prompt, "").strip()
 
-if __name__ == "__main__":
-    demo.launch()
+gr.ChatInterface(fn=chatbot, title="🩺 OpenBioLLM Chatbot", description="Ask me anything biomedical!").launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+transformers
+gradio
+torch
+accelerate