Instructions to use MrBenL/controlsense with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MrBenL/controlsense with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model = PeftModel.from_pretrained(base_model, "MrBenL/controlsense") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "mistralai/Mistral-7B-Instruct-v0.2", | |
| "lora_r": 16, | |
| "lora_alpha": 32, | |
| "lora_target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj", | |
| "gate_proj", | |
| "up_proj", | |
| "down_proj" | |
| ], | |
| "num_epochs": 3, | |
| "learning_rate": 0.0002, | |
| "training_examples": 168, | |
| "dataset": "data/training/core_examples.jsonl" | |
| } |