distilbert-base-multilingual-cased-sentiments-student
This model is distilled from the zero-shot classification pipeline on the Multilingual Sentiment dataset using this script.
Params
140 M
Context
512
Downloads 30d
795 K
Likes
317
Download history
daily snapshots · 106 days
▲ 231 K in the last 30 days (40.9%)
795 K502 K
Oct 12Oct 22Nov 1Nov 10
1.1 M502 K
Aug 13Sep 12Oct 12Nov 10
1.1 M502 K
Jul 28Sep 1Oct 6Nov 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 | f32 | 0.5 GB | 1.1 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
- DistilBertForSequenceClassification
- Parameters
- 140 M
- Tensor type
- F32
- Context length
- 512
- Vocabulary
- 119,547
- Licence
- apache-2.0
- First seen on the Hub
- 2023-05-05
- Training datasets
- tyqiangz/multilingual-sentiments
- Added to our catalog
- 2026-07-28
Compare with any text-classification model