Update app.py

app.py

@@ -1,63 +1,36 @@
 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)",
-        ),
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_name = "huggingface/llama-model"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+def chunk_text(text, chunk_size=512):
+    tokens = tokenizer.encode(text, return_tensors="pt", truncation=False)
+    chunks = [tokens[0][i:i + chunk_size] for i in range(0, tokens.size(1), chunk_size)]
+    return chunks
+
+def summarize_chunk(chunk, max_length=50):
+    summary_ids = model.generate(chunk.unsqueeze(0), max_length=max_length, min_length=25, length_penalty=2.0, num_beams=4, early_stopping=True)
+    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+    return summary
+
+def summarize(text, max_summary_length=50):
+    chunks = chunk_text(text)
+    summaries = [summarize_chunk(chunk, max_summary_length) for chunk in chunks]
+    combined_summary = " ".join(summaries)
+    final_summary = summarize_chunk(tokenizer.encode(combined_summary, return_tensors="pt", truncation=True)[0], max_length=max_summary_length)
+    return final_summary
+
+iface = gr.Interface(
+    fn=summarize,
+    inputs=[
+        gr.inputs.Textbox(lines=10, label="Input Text"),
+        gr.inputs.Slider(minimum=10, maximum=100, default=50, label="Max Summary Length (Optional)")
     ],
+    outputs="text",
+    title="Concise Text Summarization with Llama"
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()