sapBERT_NER_finetune is an open-weight model from Aswath Nag Surisetty. It has 109M parameters and a 512-token context. At 16-bit it needs about 0.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve sapBERT_NER_finetune (109M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
sapBERT_NER_finetune on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- BertForTokenClassification
- Context length (tokens)
- 512
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 30,522
- Model type
- bert
Identity and Version
- Repository
- Aswath220/sapBERT_NER_finetune
- Publisher
- Aswath Nag Surisetty
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 109M parameters
- Languages
- Not stated by the source
- Revision
- a695b3761f16bc67874a4697d1a8858e867169da
- First published
- 2026-09-29
- Last updated
- 2026-09-29
Files and Weights
6 files, 218.5 MB in total. The weights are 1 file totalling 217.8 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 217.8 MB | 9eca4b1b7c29 |
| config.json | Configuration | 872 B | — |
| train_info.json | Configuration | 289 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 706.3 KB | — |
| tokenizer_config.json | Tokenizer | 410 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 217.8 MB
Released by Aswath Nag Surisetty through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 217.8 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About sapBERT_NER_finetune
How much GPU memory does sapBERT_NER_finetune need?
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (109M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run sapBERT_NER_finetune on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is sapBERT_NER_finetune's context length?
512 tokens, from the maximum position embeddings in its published configuration.