library_name: peft | |
base_model: mistralai/Mistral-7B-v0.1 | |
pipeline_tag: text-generation | |
Description: Binary sentiment detection\ | |
Original dataset: https://huggingface.co/datasets/glue/viewer/sst2 \ | |
---\ | |
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land! \ | |
The adapter_category is Sentiment Detection and the name is Sentiment Detection (SST2)\ | |
---\ | |
Sample input: Given the following sentence:\n\nthis illuminating documentary transcends our preconceived vision of the holy land and its inhabitants , revealing the human complexities beneath . \n\nRespond with 0 if the sentiment of the sentence is negative and 1 if the sentiment of the sentence is positive.\ | |
---\ | |
Sample output: 1\ | |
---\ | |
Try using this adapter yourself! | |
``` | |
from transformers import AutoModelForCausalLM, AutoTokenizer | |
model_id = "mistralai/Mistral-7B-v0.1" | |
peft_model_id = "predibase/glue_sst2" | |
model = AutoModelForCausalLM.from_pretrained(model_id) | |
model.load_adapter(peft_model_id) | |
``` |