# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("OxxoCodes/lsg-roberta-base-4096", trust_remote_code=True)
model = AutoModelForMaskedLM.from_pretrained("OxxoCodes/lsg-roberta-base-4096", trust_remote_code=True, device_map="auto")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
In its current state, this model has not yet been finetuned on long-context data. Do not use this model without performing additional pretraining, as performance will likely suffer.
Similar to the other publicly available LSG models, this model was created using the LSG conversion script found here: https://github.com/ccdv-ai/convert_checkpoint_to_lsg
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="OxxoCodes/lsg-roberta-base-4096", trust_remote_code=True)