Upload 2 files

app.py

@@ -0,0 +1,135 @@
+import os
+
+from peft import LoraConfig, PeftModel
+
+from threading import Thread
+from typing import Iterator
+
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+model_name = "WeeRobots/phi-2-chat-v05"
+new_model = "phi-2-sheldon"
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    torch_dtype=torch.float32,
+    trust_remote_code=True
+)
+model = PeftModel.from_pretrained(base_model, new_model)
+model = model.merge_and_unload()
+
+# Reload tokenizer to save it
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "right"
+
+MAX_MAX_NEW_TOKENS = 200
+DEFAULT_MAX_NEW_TOKENS = 100
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int = 200,
+    temperature: float = 0.6,
+    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, 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=None, 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,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        print(text)
+        outputs.append(text)
+        yield "".join(outputs)
+
+
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    additional_inputs=[
+        gr.Textbox(label="System prompt", lines=3),
+        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=0.6,
+        ),
+        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?"],
+        ["How many hours does it take a man to eat a Helicopter?"],
+        ["In a Sperm bank"],
+    ],
+)
+
+with gr.Blocks() as demo:
+    chat_interface.render()
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()