Downloads · 30 days
0
hoang14/chatbot_26_8_2
chatbot_26_8_2 is a machine learning model from hoang14. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
DATASET = "task-focus + sample from remain datasets"
Downloads · 30 days
0
Access
Public
Updated Aug 26, 2023
Repo size
629 MB
Likes
0
Public
Click a slice to open those files.
.bin629 MB · 100%
From the Hugging Face model README
DATASET = "task-focus + sample from remain datasets"
DATASET_FORMAT = 'input-output'
PER_DEVICE_TRAIN_BATCH_SIZE = 2
GRADIENT_ACCUMULATION_STEPS = 4
LEARNING_RATE = 0.0003
LR_SCHEDULER_TYPE = 'constant'
WARMUP_RATIO = 0.03
LORA_R = 128
LORA_ALPHA = 32
LORA_DROPOUT = 0.1
TRAIN_ON_SOURCE = False
SOURCE_MAX_LENGTH = 1024
TARGET_MAX_LENGTH = 1024
LOGGING_STEPS = 20
SAVE_STEPS = 100
SAVE_TOTAL_LIMIT = 4