Instructions to use jeiku/Gnosis_Reformatted_Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jeiku/Gnosis_Reformatted_Mistral with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("models/TheBloke_Mistral-7B-Instruct-v0.2-GPTQ") model = PeftModel.from_pretrained(base_model, "jeiku/Gnosis_Reformatted_Mistral") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model_name": "TheBloke_Mistral-7B-Instruct-v0.2-GPTQ", | |
| "base_model_class": "MistralForCausalLM", | |
| "base_loaded_in_4bit": false, | |
| "base_loaded_in_8bit": false, | |
| "projections": "q, v", | |
| "loss": 1.1728, | |
| "learning_rate": 4.9999999999999996e-05, | |
| "epoch": 6.0, | |
| "current_steps": 277, | |
| "train_runtime": 188.9714, | |
| "train_samples_per_second": 4.71, | |
| "train_steps_per_second": 0.053, | |
| "total_flos": 152450271019008.0, | |
| "train_loss": 1.3148773193359375 | |
| } |