|
|
import gradio as gr |
|
|
import spaces |
|
|
import transformers |
|
|
import torch |
|
|
|
|
|
model_id = "joermd/speedy-llama2" |
|
|
|
|
|
pipeline = transformers.pipeline( |
|
|
"text-generation", |
|
|
model=model_id, |
|
|
model_kwargs={"torch_dtype": torch.bfloat16}, |
|
|
device_map="auto", |
|
|
) |
|
|
|
|
|
terminators = [ |
|
|
pipeline.tokenizer.eos_token_id, |
|
|
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") |
|
|
] |
|
|
|
|
|
@spaces.GPU |
|
|
def respond( |
|
|
message, |
|
|
history: list[tuple[str, str]], |
|
|
system_message, |
|
|
max_tokens, |
|
|
temperature, |
|
|
top_p, |
|
|
): |
|
|
messages = [] |
|
|
|
|
|
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}) |
|
|
|
|
|
outputs = pipeline( |
|
|
messages, |
|
|
max_new_tokens=256, |
|
|
eos_token_id=terminators, |
|
|
) |
|
|
|
|
|
yield outputs[0]["generated_text"][-1]["content"] |
|
|
|
|
|
""" |
|
|
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="Kamu adalah seorang asisten yang baik", 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)", |
|
|
), |
|
|
], |
|
|
) |
|
|
|
|
|
|
|
|
if __name__ == "__main__": |
|
|
demo.launch() |
|
|
|
