Create app.py

app.py

@@ -0,0 +1,126 @@
+#!/usr/bin/env python
+
+import os
+from collections.abc import Iterator
+from threading import Thread
+
+import gradio as gr
+import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+DESCRIPTION = "# FluentlyLM Prinum"
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+model_id = "fluently-lm/FluentlyLM-Prinum"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
+model.eval()
+
+
+@spaces.GPU(duration=120)
+def generate(
+    message: str,
+    chat_history: list[dict],
+    system_prompt: str = "",
+    max_new_tokens: int = 1024,
+    temperature: float = 0.7,
+    top_p: float = 0.8,
+    top_k: int = 20,
+    repetition_penalty: float = 1.05,
+) -> Iterator[str]:
+    messages = []
+    if system_prompt:
+        messages.append({"role": "system", "content": system_prompt})
+    messages.extend(chat_history.copy())
+    messages.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, 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=30.0, 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)
+
+
+demo = gr.ChatInterface(
+    fn=generate,
+    additional_inputs=[
+        gr.Textbox(label="System Prompt", value="You are FluentlyLM, created by Project Fluently. You are a helpful assistant."),
+        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=0.65,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.8,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=20,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.05,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["Hi! How are you?"],
+    ],
+    cache_examples=False,
+    type="messages",
+    description=DESCRIPTION,
+    css_paths="style.css",
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()