OpenMed-NER-PharmaDetect-SuperClinical-434M
Specialized model for Chemical Entity Recognition - Chemical entities from the BC5CDR dataset
Params
430 M
Context
512
Downloads 30d
279 K
Likes
33
Download history
daily snapshots · 104 days
▲ 20 K in the last 30 days (7.5%)
282 K250 K
Oct 12Oct 22Nov 1Nov 10
282 K210 K
Aug 13Sep 12Oct 12Nov 10
282 K210 K
Jul 30Sep 2Oct 7Nov 10
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 | bf16 | 0.9 GB | 1.5 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
- DebertaV2ForTokenClassification
- Parameters
- 430 M
- Tensor type
- BF16
- Context length
- 512
- Vocabulary
- 128,100
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2025-07-16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-30
Compare with any token-classification model