TienAnh
/

MoE_LlaVa_Qwen1.5_0.5b_ChartVQA_pt_shareGPT

moe_llava_qwen1_5

Generated from Trainer

Model card Files Files and versions

MoE_LlaVa_Qwen1.5_0.5b_ChartVQA_pt_shareGPT

This model is a fine-tuned version of TienAnh/stage3-moe-ft-llavaqwen1.5-0.5b-Viet-ShareGPT-2ep_moe on an unknown 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: 2e-06
train_batch_size: 4
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10.0
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.4.0
Transformers 4.37.0
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.15.1

Downloads last month: 1

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TienAnh/MoE_LlaVa_Qwen1.5_0.5b_ChartVQA_pt_shareGPT

Base model

TienAnh/stage2-ft-llavaqwen1.5-0.5B-Viet-ShareGPT-2ep

Finetuned

TienAnh/stage3-moe-ft-llavaqwen1.5-0.5b-Viet-ShareGPT-2ep_moe

Adapter

(2)

this model