LoRA (Low-Rank Adaptation of Large Language Models) for sentiment analysis task

Описание задания

В этой домашке была дообучена языковая модель Lite-Oute-1-300M-Instruct с помощью LoRA на датасете cardiffnlp/tweet_eval для задачи анализа тональности текстов

Пример генерации

Вопрос

QT @user In the original draft of the 7th book, Remus Lupin survived the Battle of Hogwarts. #HappyBirthdayRemusLupin

Ответ модели

positive 

Качество на тестовой выборке

F1 macro: 0.53

image/png

Пример запуска

from transformers import AutoModelForCausalLM, AutoTokenizer

REPO_NAME = "MurDanya/llm-course-hw3-lora"

model = AutoModelForCausalLM.from_pretrained(REPO_NAME, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(REPO_NAME)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"
Downloads last month
4
Safetensors
Model size
300M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MurDanya/llm-course-hw3-lora

Finetuned
(32)
this model

Dataset used to train MurDanya/llm-course-hw3-lora

Collection including MurDanya/llm-course-hw3-lora