Hugging Face's logo

lblaoke
/
qwama-0.5b-skywork-pref-sft-chosen-trl-v3

Safetensors
qwen2
Model card Files Community

learning_rate: 2.0e-5

num_train_epochs: 1

per_device_train_batch_size: 2

gradient_accumulation_steps: 8

Downloads last month
6
Safetensors
Model size
473M params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lblaoke/qwama-0.5b-skywork-pref-sft-chosen-trl-v3

Base model

turboderp/Qwama-0.5B-Instruct
Finetuned
(6)
this model
Finetunes
1 model

Dataset used to train lblaoke/qwama-0.5b-skywork-pref-sft-chosen-trl-v3

Collection including lblaoke/qwama-0.5b-skywork-pref-sft-chosen-trl-v3