Downloads · 30 days
3
6% of all-time downloads
Qwen2-VL-Synergy
sxj1215/Qwen2-VL-Synergy
Qwen2-VL-Synergy is a machine learning model from sxj1215. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Repo size
92.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors80.8 MB · 83%
At a glance
- Library
- peft
- License
- other
- Access
- Public
- Created
- May 25, 2025
- Updated
- May 25, 2025
- SHA
- 5001b208
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
sft_synergy_scienceqalast
This model is a fine-tuned version of Qwen/Qwen2-VL-7B-Instruct on the mmimdb, the memecap, the hateful_memes, the ny_cartoon, the memotion and the scienceqa datasets. It achieves the following results on the evaluation set:
- Loss: 0.5355
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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7891 | 0.1957 | 500 | 0.6836 |
| 0.7446 | 0.3914 | 1000 | 0.6307 |
| 0.7208 | 0.5870 | 1500 | 0.5877 |
| 0.6512 | 0.7827 | 2000 | 0.5539 |
| 0.6369 | 0.9784 | 2500 | 0.5330 |
| 0.47 | 1.1741 | 3000 | 0.5348 |
| 0.3866 | 1.3697 | 3500 | 0.5188 |
| 0.4721 | 1.5654 | 4000 | 0.5088 |
| 0.5444 | 1.7611 | 4500 | 0.4966 |
| 0.5069 | 1.9568 | 5000 | 0.4991 |
| 0.3624 | 2.1524 | 5500 | 0.5303 |
| 0.3805 | 2.3481 | 6000 | 0.5416 |
| 0.4058 | 2.5438 | 6500 | 0.5372 |
| 0.4088 | 2.7395 | 7000 | 0.5369 |
| 0.3336 | 2.9351 | 7500 | 0.5356 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.1.2+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Library
- peft
- License
- other
- Created
- May 25, 2025
- Updated
- May 25, 2025