ByteDance
/

Ouro-2.6B

Text Generation

looped-language-model

recurrent-depth

Model card Files Files and versions

Resources

View closed (1)

Fix bos/eos token IDs (config.json + tokenizer_config.json)

#5 opened 38 minutes ago by

Fix UniversalTransformerCache.get_mask_sizes for batched generation

#4 opened 38 minutes ago by

Basic web ui Inference script, updated UniversalTransformerCache in modeling_ouro.py to resolve errors.

#3 opened 25 days ago by

Lower evaluation results

#2 opened 3 months ago by