"""
NOMIC = """
TaoGPT - DataMap
"""
if not torch.cuda.is_available():
DESCRIPTION += "\nRunning on CPU 🥶 This demo does not work on CPU.
"
if torch.cuda.is_available():
model_id = "agency888/TaoGPT-v1"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, 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 = 0.6,
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.encode(f"{system_prompt}{message}", 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,
pad_token_id=2,
eos_token_id=2,
)
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=0.6,
),
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=[
["What is TaoScience ?"],
["TaoScience was written by ?"],
["Tell me more about TaoScience"]],
)
with gr.Blocks() as demo:
gr.HTML(description)
chat_interface.render()
with gr.Column():
with gr.Accordion(label="Visualise Training Data" ,open=False):
gr.HTML(NOMIC)
gr.Markdown("The model is prone to Hallucination and many not always be Factual")
if __name__ == "__main__":
demo.queue(max_size=20).launch(share=True)