mirror of
https://github.com/ParisNeo/lollms-webui.git
synced 2024-12-19 12:27:52 +00:00
70 lines
2.7 KiB
Python
70 lines
2.7 KiB
Python
######
|
|
# Project : GPT4ALL-UI
|
|
# File : backend.py
|
|
# Author : ParisNeo with the help of the community
|
|
# Supported by Nomic-AI
|
|
# Licence : Apache 2.0
|
|
# Description :
|
|
# This is an interface class for GPT4All-ui backends.
|
|
######
|
|
from pathlib import Path
|
|
from typing import Callable
|
|
from pyllamacpp.model import Model
|
|
from pyGpt4All.backend import GPTBackend
|
|
|
|
__author__ = "parisneo"
|
|
__github__ = "https://github.com/nomic-ai/gpt4all-ui"
|
|
__copyright__ = "Copyright 2023, "
|
|
__license__ = "Apache 2.0"
|
|
|
|
backend_name = "LLAMACPP"
|
|
|
|
class LLAMACPP(GPTBackend):
|
|
file_extension='*.bin'
|
|
def __init__(self, config:dict) -> None:
|
|
"""Builds a LLAMACPP backend
|
|
|
|
Args:
|
|
config (dict): The configuration file
|
|
"""
|
|
super().__init__(config, False)
|
|
|
|
self.model = Model(
|
|
model_path=f"./models/llama_cpp/{self.config['model']}",
|
|
prompt_context="", prompt_prefix="", prompt_suffix="",
|
|
n_ctx=self.config['ctx_size'],
|
|
seed=self.config['seed'],
|
|
)
|
|
|
|
def stop_generation(self):
|
|
self.model._grab_text_callback()
|
|
|
|
def generate(self,
|
|
prompt:str,
|
|
n_predict: int = 128,
|
|
new_text_callback: Callable[[str], None] = bool,
|
|
verbose: bool = False,
|
|
**gpt_params ):
|
|
"""Generates text out of a prompt
|
|
|
|
Args:
|
|
prompt (str): The prompt to use for generation
|
|
n_predict (int, optional): Number of tokens to prodict. Defaults to 128.
|
|
new_text_callback (Callable[[str], None], optional): A callback function that is called everytime a new text element is generated. Defaults to None.
|
|
verbose (bool, optional): If true, the code will spit many informations about the generation process. Defaults to False.
|
|
"""
|
|
try:
|
|
self.model.reset()
|
|
for tok in self.model.generate(prompt,
|
|
n_predict=n_predict,
|
|
temp=self.config['temperature'],
|
|
top_k=self.config['top_k'],
|
|
top_p=self.config['top_p'],
|
|
repeat_penalty=self.config['repeat_penalty'],
|
|
repeat_last_n = self.config['repeat_last_n'],
|
|
n_threads=self.config['n_threads'],
|
|
):
|
|
if not new_text_callback(tok):
|
|
return
|
|
except Exception as ex:
|
|
print(ex) |