Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
tmp_Qwen3-VL-4B-LLaVAOV-Stage2-mbs1_h200 – AI Model by lewei123 | AlphaNeural AI
You can deploy this model and start earning money today!
lewei123
/
tmp_Qwen3-VL-4B-LLaVAOV-Stage2-mbs1_h200
like
0
transformers
safetensors
qwen3_vl
image-text-to-text
llama-factory
full
generated_from_trainer
conversational
other
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
stage2_instruct_res_1024
This model is a fine-tuned version of
saves/qwen3_vl_4b/llava_ov_train_fix_prompt_npumbs/stage1_5_midtrain
on the llava_ov_1_5_instruct dataset.
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: 1e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 28
total_train_batch_size: 224
total_eval_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.99) and epsilon=1e-05 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_ratio: 0.002
training_steps: 3500
Training results
Framework versions
Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.22.1
