Downloads · 30 days
6
7% of all-time downloads
lblaoke/qwama-0.5b-skywork-pref-dpo-llama-factory-v1
qwama-0.5b-skywork-pref-dpo-llama-factory-v1 is a machine learning model from lblaoke. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
6
7% of all-time downloads
All-time downloads
90
Public
Parameters
473M
963 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors946 MB · 98%
From the Hugging Face model README
lora_rank: 32
pref_beta: 0.1
cutoff_len: 2048
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
learning_rate: 5.0e-6
num_train_epochs: 1.0
lr_scheduler_type: cosine
warmup_ratio: 0.1