Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
siq-vl_siglip2-so400m-patch14-224_qwen3-0.6b-base_stage1 – AI Model by duoan | AlphaNeural AI
You can deploy this model and start earning money today!
duoan
/
siq-vl_siglip2-so400m-patch14-224_qwen3-0.6b-base_stage1
like
0
transformers
pytorch
siq_vl
text-generation
generated_from_trainer
conversational
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
siq-vl_siglip2-so400m-patch14-224_qwen3-0.6b-base_stage1
This model is a fine-tuned version of
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 13.6539
Num Input Tokens Seen: 82288861
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: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Use adamw_torch_fused 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: 0.03
training_steps: 5000
Training results
Framework versions
Transformers 4.57.3
Pytorch 2.9.1+cu130
Datasets 4.4.1
Tokenizers 0.22.1
