tachikoma-v0.9

This model is a fine-tuned version of jaigouk/tachikoma-v1 on an unknown dataset.

Model description

• intention is to use this with system message for generating ruby codes
• license: cc-by-nc-4.0
• base_model: jaigouk/tachikoma-v0

Intended uses & limitations

• writing rspec / ruby codes
• https://ollama.ai/jaigouk/tachikoma

Training and evaluation data

• https://huggingface.co/datasets/jaigouk/coding-dataset
• https://huggingface.co/datasets/jondurbin/airoboros-3.1
• https://huggingface.co/datasets/LDJnr/Capybara
• https://huggingface.co/datasets/garage-bAInd/Open-Platypus

Training procedure

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_steps: 1 - num_epochs: 1

Training results

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1