Downloads · 30 days
20
34% of all-time downloads
gemma-2-2b-it-MT-DPO
martimfasantos/gemma-2-2b-it-MT-DPO
gemma-2-2b-it-MT-DPO is a translation model from martimfasantos. Use it when you need text moved from one language to another. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Parameters
2.6B
5.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.2 GB · 100%
At a glance
- Task
- Translation
- License
- gemma
- Model type
- gemma2
- Access
- Public
- Created
- Sep 30, 2024
- Updated
- Dec 30, 2024
- SHA
- 4d1b5f45
Try a prompt
Base models
Datasets
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. -->
gemma-2-2b-it-MT-DPO
This model is a fine-tuned version of martimfasantos/gemma-2-2b-it-MT-SFT on the sardinelab/MT-pref 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: 1e-07
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Translation
- Type
- gemma2
- License
- gemma
- Created
- Sep 30, 2024
- Updated
- Dec 30, 2024