Instructions to use erave02/checkppoint128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use erave02/checkppoint128 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("models/llama-2-13b/model_artifacts/training_weights") model = PeftModel.from_pretrained(base_model, "erave02/checkppoint128") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "models/llama-2-13b/model_artifacts/training_weights", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 256, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 128, | |
| "revision": null, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |