Training
Hugging Face Fine-Tuning for Question Answering
Learn about the hf_finetune_llm_qa
function within Simplifine’s Train Engine
hf_finetune_llm_qa(
model_name:str,
dataset_name:str='',
from_hf:bool=False,
queries:list=[],
context:list=[],
answers:list=[],
hf_token:str=''
):
model_name
string
requiredThe name or path of the pre-trained model to use.
dataset_name
string
The name of the dataset to be used for fine-tuning. Defaults to an empty string.
from_hf
boolean
A flag to determine whether to load the dataset from Hugging Face. Defaults to False
.
queries
list
A list of questions (queries) for fine-tuning the model. Defaults to an empty list.
context
list
A list of contexts related to the queries. Defaults to an empty list.
answers
list
A list of answers corresponding to the queries. Defaults to an empty list.
hf_token
string
The Hugging Face token required for accessing private datasets or models. Defaults to an empty string.