mantis-8b-idefics2__8192
This model is a fine-tuned version of TIGER-Lab/Mantis-8B-Idefics2 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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- 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: 30.0
Training results
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 17
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for francepfl/mantis-8b-idefics2__8192
Base model
HuggingFaceM4/idefics2-8b
Finetuned
TIGER-Lab/Mantis-8B-Idefics2