Hugging Face's logo

lblaoke
/
qwama-0.5b-hh-rlhf-sft-chosen-trl-v4

Safetensors
qwen2
Model card Files Community

num_train_epochs: 1

learning_rate: 2e-4

total_batch_size: 32

Downloads last month
7
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-hh-rlhf-sft-chosen-trl-v4

Base model

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

Dataset used to train lblaoke/qwama-0.5b-hh-rlhf-sft-chosen-trl-v4

Collection including lblaoke/qwama-0.5b-hh-rlhf-sft-chosen-trl-v4