Upload 2 files

huggingface_int V2.py

@@ -0,0 +1,31 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the tokenizer and model directly
+model_name = "ruslanmv/ai-medical-model-32bit"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+model.to("cuda")  # Move model to GPU
+
+
+# Function to ask medical questions
+def ask_medical_question(question):
+    prompt = f"<|start_header_id|>system<|end_header_id|> You are a Medical AI chatbot assistant. <|eot_id|><|start_header_id|>User: <|end_header_id|>This is the question: {question}<|eot_id|>"
+
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        temperature=0.7,
+        do_sample=True,
+        top_p=0.95,
+        top_k=50,
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+
+# Set up Gradio interface
+iface = gr.Interface(fn=ask_medical_question, inputs="text", outputs="text")
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch