Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
DINOCOMPANION – Dataset by Beaconsyh08 | AlphaNeural AI
You can deploy this model and start earning money today!
Beaconsyh08
/
DINOCOMPANION
like
0
mit
n<1K
imagefolder
image
datasets
mlcroissant
us
Views
No views yet
Model card
Files and Versions
Community
API
sft_fulldata_clean
This model is a fine-tuned version of
Qwen/Qwen3-32B
on the dino_1_merged, the dino_cp_merged and the dino_character_merged 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: 0.0001
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 64
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: 0.1
num_epochs: 20
Training results
Framework versions
PEFT 0.15.1
Transformers 4.51.0
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.21.0
