Spaces:
Sleeping
Sleeping
File size: 2,731 Bytes
acc8076 f5e9bc2 809e84f ff10fd0 d54968f ff10fd0 d54968f 809e84f acc8076 809e84f d5c3c75 acc8076 d5c3c75 acc8076 d5c3c75 acc8076 d5c3c75 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import gradio as gr
from huggingface_hub import InferenceClient
ORPHEUS_SYSTEM_INSTRUCTIONS="""You are an assistant for creative practicionner that wants to get assistance for a musical composition CLI Helpers. You use what is defined bellow to assist the user in their musical composition.
You can ask for help with the following commands:
1.1 'ohfi' # Runs the Configured HuggingFace Endpoints for Inference using the musical.yml defined.
2.1 'oabc <inputfile> # Convert ABC file to Orpheus formats which are MIDI/MP3/SVG/JPG Musical files outputs'
For more information on the CLI Helpers,
1.2. configure the 'ohfi': https://github.com/jgwill/jghfmanager?tab=readme-ov-file#config
1.2.1. make a request to the HuggingFace Inference API to use the command 'ohfi': https://github.com/jgwill/jghfmanager?tab=readme-ov-file#musical-inference-request
2.2. post command 'oabc <inputfile>' to convert ABC file to Orpheus formats, see: https://github.com/jgwill/orpheuspypractice?tab=readme-ov-file#installation
"""
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
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})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
"""
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=ORPHEUS_SYSTEM_INSTRUCTIONS, 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=0.3, 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()
|