Downloads · 30 days
13
6% of all-time downloads
fffonion/xlm-roberta-ner-japanese-gguf
xlm-roberta-ner-japanese-gguf is a machine learning model from fffonion. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Japanese NER (Named Entity Recognition) model in GGUF format for efficient CPU inference via llama.cpp / Candle.
Downloads · 30 days
13
6% of all-time downloads
All-time downloads
230
Public
Repo size
865 MB
Likes
2
Public
Click a slice to open those files.
.gguf865 MB · 100%
From the Hugging Face model README
Japanese NER (Named Entity Recognition) model in GGUF format for efficient CPU inference via llama.cpp / Candle.
| File | Type | Size | Description |
|---|---|---|---|
xlm-roberta-ner-japanese-f16.gguf | FP16 | 536MB | Full precision, best quality |
xlm-roberta-ner-japanese-q8_0.gguf | Q8_0 | 290MB | 8-bit quantized, recommended |
let model = candle_ner::Model::load(&device, "xlm-roberta-ner-japanese-q8_0.gguf")?;
let input = "山田太郎は東京大学に通っている";
let entities = model.predict(input)?;
| ID | Label | Description |
|---|---|---|
| 0 | O | Outside entity |
| 1 | PER | Person |
| 2 | ORG | Organization |
| 3 | ORG-P | Organization-Prefix |
| 4 | ORG-O | Organization-Other |
| 5 | LOC | Location |
| 6 | INS | Instrument |
| 7 | PRD | Product |
| 8 | EVT | Event |
FP16 → Q8_0 quantization done with llama.cpp:
./llama-quantize xlm-roberta-ner-japanese-f16.gguf \
xlm-roberta-ner-japanese-q8_0.gguf Q8_0