Upcycling Experiments
Collection
Models I pre-trained initialising SMoE models using dense model weights and the upcycling process used for Qwen1.5-MoE2.7BA (or something similar)
•
6 items
•
Updated
first
This model is a fine-tuned version of gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B on the wiki_demo 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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7
Model tree for gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B-LoRA
Base model
gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B