Instructions to use HideIron/tiny-aya-global-sql-selfheal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HideIron/tiny-aya-global-sql-selfheal with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global") model = PeftModel.from_pretrained(base_model, "HideIron/tiny-aya-global-sql-selfheal") - Notebooks
- Google Colab
- Kaggle
Download training_stats.json from HideIron/tiny-aya-global-sql-selfheal: direct link, hf CLI and curl.
- Browser
- Download file 1.47 kB
-
https://huggingface.co/HideIron/tiny-aya-global-sql-selfheal/resolve/main/training_stats.json
- Command line
-
hf download hf://HideIron/tiny-aya-global-sql-selfheal/training_stats.json
-
curl -L -o training_stats.json https://huggingface.co/HideIron/tiny-aya-global-sql-selfheal/resolve/main/training_stats.json
1.47 kB
| { | |
| "model": "CohereLabs/tiny-aya-global", | |
| "dataset_name": "unknown", | |
| "output_dir": "/tmp/out/adapter", | |
| "use_rollouts": false, | |
| "agentic_mode": false, | |
| "tools": [], | |
| "train_size": 153, | |
| "eval_size": 0, | |
| "final_loss": 0.3636344361305237, | |
| "total_steps": 50, | |
| "training_history": [], | |
| "metrics": { | |
| "train_runtime": 1543.1982, | |
| "train_samples_per_second": 0.496, | |
| "train_steps_per_second": 0.032, | |
| "total_flos": 2.622984019611648e+16, | |
| "train_loss": 0.3636344361305237, | |
| "epoch": 5.0 | |
| }, | |
| "config_kwargs": { | |
| "model": "CohereLabs/tiny-aya-global", | |
| "train_dataset": "Dataset({\n features: ['prompt', 'chosen', 'rejected'],\n num_rows: 153\n})", | |
| "output_dir": "/tmp/out/adapter", | |
| "peft_config": { | |
| "r": 16, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "task_type": "CAUSAL_LM", | |
| "target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj", | |
| "gate_proj", | |
| "up_proj", | |
| "down_proj" | |
| ] | |
| }, | |
| "num_train_epochs": 5.0, | |
| "per_device_train_batch_size": 1, | |
| "gradient_accumulation_steps": 16, | |
| "learning_rate": 2e-05, | |
| "beta": 0.1, | |
| "seed": 42, | |
| "bf16": true, | |
| "logging_steps": 2, | |
| "save_strategy": "no", | |
| "report_to": "none", | |
| "gradient_checkpointing": true, | |
| "model_init_kwargs": { | |
| "dtype": "bfloat16", | |
| "trust_remote_code": false | |
| }, | |
| "max_prompt_length": 2048, | |
| "max_length": 2176 | |
| } | |
| } |