Instructions to use josh-oo/calibrated-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use josh-oo/calibrated-decoder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("josh-oo/calibrated-decoder") model = AutoModelForSeq2SeqLM.from_pretrained("josh-oo/calibrated-decoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Distilled layers: [-1] (0.75) kr/vr
bb7f14a
-
Distilled layers: [r, r, -1] (0.75) kr/vr
f2e4680
-
Distilled layers: [r, r, -1] (0.75) kr/vr
462d88f
-
Distilled layers: [r, r, -1] (0.75)
c77f7fc
-
Trained with normal text replication (+ bart noise [Multilingual BERT])
1bf3259
-
Finetuned on simplification task
4f1357e
-
Trained with normal text replication (+ bart noise [ + CTRL Tokens])
3ff0b79
-
Trained with normal text replication (+ bart noise [Multilingual BERT])
ef48566
-
Trained with normal text replication [mlsum] (+ bart noise)
c7ef61e
-
Trained with normal text replication (+ bart noise [only permutation])
b7defb2
-
Trained with normal text replication (+ bart noise [only masking])
729966d -
Trained with normal text replication (+ bart noise)
7bf0045
-
Trained with normal text replication
28295ad
-
Update config.json
fa840f3 -
Initial commit
fcca31e -
initial commit
Joshua Oehms4a313a6