Update app.py

app.py

@@ -1,135 +1,24 @@
-# From https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat
-import os
-from threading import Thread
-from typing import Iterator
+from sonique import get_pretrained_model
+from sonique.interface.gradio import create_ui
+import json 
 
-import gradio as gr
-import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-MAX_MAX_NEW_TOKENS = 2048
-DEFAULT_MAX_NEW_TOKENS = 1024
-MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
+def main(args):
+    torch.manual_seed(42)
 
-DESCRIPTION = """
-# Chat with Failure 2B Base
-
-Chat with [Failure 2B Base](https://huggingface.co/mrfakename/failure-2b-base).
-
----
-
-A quick failed experiment at creating a SLM that can code. Based on [Danube](https://huggingface.co/h2oai/h2o-danube-1.8b-base).
-
-Scored 14.8% on HumanEval (FWIW I personally recommend using a quantized 7B model for coding instead of a SLM). Open-sourcing for transparency.
-"""
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n\nRunning on CPU 🥶 This demo does not work on CPU."
-
-if torch.cuda.is_available():
-    model_id = "mrfakename/failure-2b-base"
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    tokenizer.use_default_system_prompt = False
-
-
-@spaces.GPU
-def generate(
-    message: str,
-    chat_history: list[tuple[str, str]],
-    system_prompt: str,
-    max_new_tokens: int = 1024,
-    temperature: float = 0.2,
-    top_p: float = 0.9,
-    top_k: int = 50,
-    repetition_penalty: float = 1.2,
-) -> Iterator[str]:
-    conversation = []
-    if system_prompt:
-        conversation.append({"role": "system", "content": system_prompt})
-    for user, assistant in chat_history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
-
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
-
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
-
-
-chat_interface = gr.ChatInterface(
-    fn=generate,
-    additional_inputs=[
-        gr.Textbox(label="System prompt", lines=6),
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.2,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
-    stop_btn=None,
-    examples=[
-        ["Hello there! How are you doing?"],
-        ["Please explain the Python programming language to me."],
-        ["Please write a function in Python to calculate the fibonacci sequence."],
-        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
-    ],
-)
-
-with gr.Blocks() as demo:
-    gr.Markdown(DESCRIPTION)
-    chat_interface.render()
+    interface = create_ui(model_config_path = args.model_config, ckpt_path=args.ckpt_path, pretrained_name=args.pretrained_name, pretransform_ckpt_path=args.pretransform_ckpt_path)
+    interface.queue()
+    interface.launch(share=True, auth=(args.username, args.password) if args.username is not None else None)
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    import argparse
+    parser = argparse.ArgumentParser(description='Run gradio interface')
+    parser.add_argument('--pretrained-name', type=str, help='Name of pretrained model', required=False)
+    parser.add_argument('--model-config', type=str, help='Path to model config', required=False)
+    parser.add_argument('--ckpt-path', type=str, help='Path to model checkpoint', required=False)
+    parser.add_argument('--pretransform-ckpt-path', type=str, help='Optional to model pretransform checkpoint', required=False)
+    parser.add_argument('--username', type=str, help='Gradio username', required=False)
+    parser.add_argument('--password', type=str, help='Gradio password', required=False)
+    args = parser.parse_args()
+    main(args)