Update app.py

app.py

@@ -1,63 +1,42 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-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)",
-        ),
-    ],
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "Writer/Palmyra-Med-70B-32k"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    attn_implementation="flash_attention_2",
 )
 
+messages = [
+    {
+        "role": "system",
+        "content": "You are a highly knowledgeable and experienced expert in the healthcare and biomedical field, possessing extensive medical knowledge and practical expertise.",
+    },
+    {
+        "role": "user",
+        "content": "Does danzhi Xiaoyao San ameliorate depressive-like behavior by shifting toward serotonin via the downregulation of hippocampal indoleamine 2,3-dioxygenase?",
+    },
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+)
+
+gen_conf = {
+    "max_new_tokens": 256,
+    "eos_token_id": [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")],
+    "temperature": 0.0,
+    "top_p": 0.9,
+}
+
+with torch.inference_mode():
+    output_id = model.generate(input_ids, **gen_conf)
+
+output_text = tokenizer.decode(output_id[0][input_ids.shape[1] :])
 
-if __name__ == "__main__":
-    demo.launch()
+print(output_text)