Downloads · 30 days
5
4% of all-time downloads
odia-paligemma-2b-9900-v1.1
sam2ai/odia-paligemma-2b-9900-v1.1
odia-paligemma-2b-9900-v1.1 is a machine learning model from sam2ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
131
Public
Parameters
2.9B
36.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt31 GB · 84%
At a glance
- License
- other
- Model type
- paligemma
- Access
- Public
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024
- SHA
- 9de03ecd
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. -->
paligemma-3b-odia-chat-final
This model is a fine-tuned version of google/paligemma-3b-mix-448 on the odia_llava_data 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: 3e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 10.0
Training results
Framework versions
- Transformers 4.43.2
- Pytorch 2.1.2+git70dfd51
- Datasets 2.19.1
- Tokenizers 0.19.1
- Type
- paligemma
- License
- other
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024