Quantization made by Richard Erkhov.
SpecAI - bnb 4bits
- Model creator: https://huggingface.co/gtonkov/
- Original model: https://huggingface.co/gtonkov/SpecAI/
Original model description:
library_name: transformers license: other base_model: microsoft/Phi-3.5-mini-instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: SpecAI results: []
SpecAI
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the api_eval_dataset 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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 32.0
Training results
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1