Downloads · 30 days
19
21% of all-time downloads
tFINE-900m-e16-d32-1024ctx
pszemraj/tFINE-900m-e16-d32-1024ctx
tFINE-900m-e16-d32-1024ctx is a text generation model from pszemraj. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
90
Public
Parameters
887M
24.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors28.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Aug 31, 2024
- Updated
- Dec 29, 2025
- SHA
- 04d4cf9d
Try a prompt
Datasets
Model card
From the Hugging Face model README
tFINE-900m-e16-d32-1024ctx
Pretrained T5 model with nanoT5:
- ~900m parameters, 16 layers in encoder, 32 layers in decoder
- sentencepiece tokenizer with 48k vocab & byte-pair fallback
- handles whitespaces etc correctly (unlike original T5 tokenizer)
- 1024 ctx during pretrain
relative_attention_num_bucketsincreased to 48 from 32 for context length upscaling
Experiment logs
Training consisted of two phases:
- Task
- Text Generation
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Languages
- en
- Created
- Aug 31, 2024
- Updated
- Dec 29, 2025