mLLMs_merging_4_DMO
Collection
Official checkpoints from the paper "Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization". • 22 items • Updated
Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization
This is an official checkpoint from the paper: "Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization " (link). See the official implementation for more information on how to use the models.
qwen2_2b_lora_mixed-102400
This repo contains fine-tuned versions of Qwen/Qwen2-VL-2B on diverse dataset mixtures of Chart, Counting, GeneralVQA, and OCR data (~100k samples).
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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: 0.1
- training_steps: 800
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for daviBera/qwen2_2b_lora_mixed-102400
Base model
Qwen/Qwen2-VL-2B