Spaces:
Sleeping
Sleeping
File size: 2,217 Bytes
bf6d237 7344079 bf6d237 7344079 bf6d237 7344079 |
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 |
import logging
from injector import inject, singleton
from llama_index.llms import MockLLM
from llama_index.llms.base import LLM
from private_gpt.components.llm.prompt_helper import get_prompt_style
from private_gpt.paths import models_path
from private_gpt.settings.settings import Settings
import os
logger = logging.getLogger(__name__)
@singleton
class LLMComponent:
llm: LLM
@inject
def __init__(self, settings: Settings) -> None:
llm_mode = settings.llm.mode
logger.info("Initializing the LLM in mode=%s", llm_mode)
match settings.llm.mode:
case "local":
from llama_index.llms import LlamaCPP
prompt_style_cls = get_prompt_style(settings.local.prompt_style)
prompt_style = prompt_style_cls(
default_system_prompt=settings.local.default_system_prompt
)
self.llm = LlamaCPP(
model_path=str(models_path / settings.local.llm_hf_model_file),
temperature=0.1,
max_new_tokens=settings.llm.max_new_tokens,
# llama2 has a context window of 4096 tokens,
# but we set it lower to allow for some wiggle room
context_window=3900,
generate_kwargs={},
# All to GPU
model_kwargs={"n_gpu_layers": -1},
# transform inputs into Llama2 format
messages_to_prompt=prompt_style.messages_to_prompt,
completion_to_prompt=prompt_style.completion_to_prompt,
verbose=True,
)
case "sagemaker":
from private_gpt.components.llm.custom.sagemaker import SagemakerLLM
self.llm = SagemakerLLM(
endpoint_name=settings.sagemaker.llm_endpoint_name,
)
case "openai":
from llama_index.llms import OpenAI
openai_settings = os.environ.get("OPENAI_API_KEY")
self.llm = OpenAI(model="gpt-4",api_key=openai_settings)
case "mock":
self.llm = MockLLM()
|