Instructions to use predibase/hellaswag_processed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use predibase/hellaswag_processed with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1") model = PeftModel.from_pretrained(base_model, "predibase/hellaswag_processed") - Notebooks
- Google Colab
- Kaggle
| library_name: peft | |
| base_model: mistralai/Mistral-7B-v0.1 | |
| pipeline_tag: text-generation | |
| Description: Sentence completion\ | |
| Original dataset: https://huggingface.co/datasets/Rowan/hellaswag \ | |
| ---\ | |
| Try querying this adapter for free in Lora Land at https://predibase.com/lora-land! \ | |
| The adapter_category is Other and the name is Open-Ended Sentence Completion (hellaswag)\ | |
| ---\ | |
| Sample input: You are provided with an incomplete passage below. Please read the passage and then finish it with an appropriate response. For example:\n\n### Passage: My friend and I think alike. We\n\n### Ending: often finish each other's sentences.\n\nNow please finish the following passage:\n\n### Passage: Numerous people are watching others on a field. Trainers are playing frisbee with their dogs. the dogs\n\n### Ending: \ | |
| ---\ | |
| Sample output: are running around the field.\ | |
| ---\ | |
| Try using this adapter yourself! | |
| ``` | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model_id = "mistralai/Mistral-7B-v0.1" | |
| peft_model_id = "predibase/hellaswag_processed" | |
| model = AutoModelForCausalLM.from_pretrained(model_id) | |
| model.load_adapter(peft_model_id) | |
| ``` |