English
Edit model card

This is RedPajama-INCITE-Bse-3B-v1, fine-tuned to generate children wikipedia headings. The input should be "root>downto>bottom:", e.g.: "Mathematics>History>19-th Century:". The output shuold be seperated by "|"

Usage

from peft import *
from transformers import *
peft_path='umarzein/INCITE-WikipediaHeadings'
base_path="togethercomputer/RedPajama-INCITE-Base-3B-v1"
base=AutoModelForCausalLM.from_pretrained(base_path)
tokenizer=AutoTokenizer.from_pretrained(base_path)
model=PeftModel(base,peft_path)
output=model.generate(input_ids=tokenizer("Mathematics:",return_tensors='pt')['input_ids'])
decoded=tokenizer.decode(output.flatten())
#Mathematics:History|Etymology|Areas of mathematics
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train umarzein/INCITE-WikipediaHeadings