Update app.py

app.py

@@ -1,95 +1,25 @@
-from huggingface_hub import InferenceClient
 import gradio as gr
-
-client = InferenceClient(
-    "thviet79/model-QA-medical-2024"
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model (SafeTensors format) from Hugging Face model hub
+model_name = "your-model-name"  # Replace with the actual model ID that supports SafeTensors
+model = AutoModelForCausalLM.from_pretrained("thviet79/model-QA-medical-2024", use_safetensors=True)
+tokenizer = AutoTokenizer.from_pretrained("thviet79/model-QA-medical-2024")
+
+# Function to generate responses using the model
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(inputs["input_ids"], max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs="text",
+    outputs="text",
+    title="SafeTensors Model Chatbot",
+    description="Ask anything to the model loaded from SafeTensors"
 )
 
-
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
-    )
-
-    formatted_prompt = format_prompt(prompt, history)
-
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
-
-
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=256,
-        minimum=0,
-        maximum=1048,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
-
-
-gr.ChatInterface(
-    fn=generate,
-    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, layout="panel"),
-    additional_inputs=additional_inputs,
-    title="""Mistral 7B v0.3"""
-).launch(show_api=False)
-
-
-gr.load("HuggingFaceH4/zephyr-7b-beta").launch()
-
-gr.load("Viet-Mistral/Vistral-7B-Chat").launch()
+# Launch the Gradio interface
+iface.launch()