library_name: peft | |
base_model: mistralai/Mistral-7B-v0.1 | |
pipeline_tag: text-generation | |
Description: Translation from meaning representation to natural language\ | |
Original dataset: https://huggingface.co/datasets/e2e_nlg \ | |
---\ | |
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land! \ | |
The adapter_category is Structured-to-Text and the name is Structured-to-Text (e2e_nlg)\ | |
---\ | |
Sample input: You are given a meaning representation below. Please translate it into plain English. Here is an example:\n\n### Meaning Representation: name[Blue Spice], eatType[coffee shop], area[city centre]\n\n### Plain English: A coffee shop in the city centre area called Blue Spice.\n\nNow please translate the following meaning representation:\n\n### Meaning Representation: name[Blue Spice], eatType[pub], food[Chinese], area[city centre], familyFriendly[yes], near[Rainbow Vegetarian Café]\n\n### Plain English:\ | |
---\ | |
Sample output: Blue Spice is a pub that serves Chinese food. It is located in the city centre near Rainbow Vegetarian Café.\ | |
---\ | |
Try using this adapter yourself! | |
``` | |
from transformers import AutoModelForCausalLM, AutoTokenizer | |
model_id = "mistralai/Mistral-7B-v0.1" | |
peft_model_id = "predibase/e2e_nlg" | |
model = AutoModelForCausalLM.from_pretrained(model_id) | |
model.load_adapter(peft_model_id) | |
``` |