Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
STAR-1_Qwen3-8B_safety_dpo_over_refusal_mix – AI Model by hlttxdy | AlphaNeural AI
You can deploy this model and start earning money today!
hlttxdy
/
STAR-1_Qwen3-8B_safety_dpo_over_refusal_mix
like
0
transformers
safetensors
qwen3
text-generation
llama-factory
full
generated_from_trainer
conversational
Qwen/Qwen3-8B
finetune
other
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
safep0.5_epoch1_lr5e-6_beta0.05_ftx0.2
This model is a fine-tuned version of
Qwen/Qwen3-8B
on the STAR-1_Qwen3-8B_dpo_own and the STAR-1_Qwen3-8B_dpo_own_over_refusal datasets.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1.0
Training results
Framework versions
Transformers 4.51.3
Pytorch 2.7.1+cu126
Datasets 3.2.0
Tokenizers 0.21.1
