mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-23 16:38:21 +01:00
88 lines
2.6 KiB
Python
88 lines
2.6 KiB
Python
import asyncio
|
|
import json
|
|
import sys
|
|
|
|
try:
|
|
import websockets
|
|
except ImportError:
|
|
print("Websockets package not found. Make sure it's installed.")
|
|
|
|
# For local streaming, the websockets are hosted without ssl - ws://
|
|
HOST = 'localhost:5005'
|
|
URI = f'ws://{HOST}/api/v1/stream'
|
|
|
|
# For reverse-proxied streaming, the remote will likely host with ssl - wss://
|
|
# URI = 'wss://your-uri-here.trycloudflare.com/api/v1/stream'
|
|
|
|
|
|
async def run(context):
|
|
# Note: the selected defaults change from time to time.
|
|
request = {
|
|
'prompt': context,
|
|
'max_new_tokens': 250,
|
|
'auto_max_new_tokens': False,
|
|
'max_tokens_second': 0,
|
|
|
|
# Generation params. If 'preset' is set to different than 'None', the values
|
|
# in presets/preset-name.yaml are used instead of the individual numbers.
|
|
'preset': 'None',
|
|
'do_sample': True,
|
|
'temperature': 0.7,
|
|
'top_p': 0.1,
|
|
'typical_p': 1,
|
|
'epsilon_cutoff': 0, # In units of 1e-4
|
|
'eta_cutoff': 0, # In units of 1e-4
|
|
'tfs': 1,
|
|
'top_a': 0,
|
|
'repetition_penalty': 1.18,
|
|
'additive_repetition_penalty': 0,
|
|
'repetition_penalty_range': 0,
|
|
'top_k': 40,
|
|
'min_length': 0,
|
|
'no_repeat_ngram_size': 0,
|
|
'num_beams': 1,
|
|
'penalty_alpha': 0,
|
|
'length_penalty': 1,
|
|
'early_stopping': False,
|
|
'mirostat_mode': 0,
|
|
'mirostat_tau': 5,
|
|
'mirostat_eta': 0.1,
|
|
'grammar_string': '',
|
|
'guidance_scale': 1,
|
|
'negative_prompt': '',
|
|
|
|
'seed': -1,
|
|
'add_bos_token': True,
|
|
'truncation_length': 2048,
|
|
'ban_eos_token': False,
|
|
'custom_token_bans': '',
|
|
'skip_special_tokens': True,
|
|
'stopping_strings': []
|
|
}
|
|
|
|
async with websockets.connect(URI, ping_interval=None) as websocket:
|
|
await websocket.send(json.dumps(request))
|
|
|
|
yield context # Remove this if you just want to see the reply
|
|
|
|
while True:
|
|
incoming_data = await websocket.recv()
|
|
incoming_data = json.loads(incoming_data)
|
|
|
|
match incoming_data['event']:
|
|
case 'text_stream':
|
|
yield incoming_data['text']
|
|
case 'stream_end':
|
|
return
|
|
|
|
|
|
async def print_response_stream(prompt):
|
|
async for response in run(prompt):
|
|
print(response, end='')
|
|
sys.stdout.flush() # If we don't flush, we won't see tokens in realtime.
|
|
|
|
|
|
if __name__ == '__main__':
|
|
prompt = "In order to make homemade bread, follow these steps:\n1)"
|
|
asyncio.run(print_response_stream(prompt))
|