long-t5-tglobal-base-sci-simplify
Exploring how well long-document models trained on "lay summaries" of scientific papers generalize.
Params
248 M
Context
—
Downloads 30d
208 K
Likes
10
Download history
daily snapshots · 24 days208 K43 K
Oct 1Oct 9Oct 17Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 1.0 GB | 1.6 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- LongT5ForConditionalGeneration
- Parameters
- 248 M
- Tensor type
- F32
- Vocabulary
- 32,128
- Licence
- apache-2.0
- First seen on the Hub
- 2023-04-06
- Training datasets
- pszemraj/scientific_lay_summarisation-plos-norm
- Added to our catalog
- 2026-10-01
Compare with any summarization model