Open-weight model
ucu-wsd-aug16-generation_shuffling_pt-false_seed-456
by Yurii Laba yuriilaba/ucu-wsd-aug16-generation_shuffling_pt-false_seed-456
ucu-wsd-aug16-generation_shuffling_pt-false_seed-456 is an open-weight model from Yurii Laba. It has 278M parameters and a 514-token context. At 16-bit it needs about 0.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Fine-tuned Ukrainian word-sense-disambiguation model. - Full MTEB task-level results are in evaluation/mtebresults/.
Runs On
What it takes to serve ucu-wsd-aug16-generation_shuffling_pt-false_seed-456 (278M 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 | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 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.
Model Card
Fine-tuned Ukrainian word-sense-disambiguation model. - Full MTEB task-level results are in evaluation/mtebresults/.
Excerpt from the card by Yurii Laba.
Configuration
- Architecture
- XLMRobertaModel
- Context length (tokens)
- 514
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 250,002
- Model type
- xlm-roberta
Identity and Version
- Repository
- yuriilaba/ucu-wsd-aug16-generation_shuffling_pt-false_seed-456
- Publisher
- Yurii Laba
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 278M parameters
- Languages
- xlm-roberta
- Revision
- 4d0ed4fbbc1de1a6e7fc172a90d17fbe4ab1b56c
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
8 files, 1.1 GB in total. The weights are 1 file totalling 1.1 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | 736447fe9c10 |
| config.json | Configuration | 809 B | — |
| config_sentence_transformers.json | Configuration | 284 B | — |
| evaluation/metrics.json | Configuration | 99.5 KB | — |
| README.md | Documentation | 589 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | cad551d5600a |
| tokenizer_config.json | Tokenizer | 534 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Released by Yurii Laba through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About ucu-wsd-aug16-generation_shuffling_pt-false_seed-456
How much GPU memory does ucu-wsd-aug16-generation_shuffling_pt-false_seed-456 need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run ucu-wsd-aug16-generation_shuffling_pt-false_seed-456 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 ucu-wsd-aug16-generation_shuffling_pt-false_seed-456's context length?
514 tokens, from the maximum position embeddings in its published configuration.