MDL
opt-1.3b
Parameters
1.3B
Downloads
863.7K
on HF
Likes
184
Avg score
—
Weights
Open
Released
May 11, 2022
About
opt-1.3b is a 1.3B-parameter open-weights model in the opt family from facebook.
othertext-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →OPT: Open Pre-trained Transformer Language ModelsLanguage Models are Few-Shot LearnersLLM Zeroth-Order Fine-Tuning is an Inference WorkloadMay 27, 2026Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax DiesMay 20, 2026PACZero: PAC-Private Fine-Tuning of Language Models via Sign QuantizationMay 7, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.