Instructions to use pooria/foxmind-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use pooria/foxmind-small with Transformers.js:
// ⚠️ Unknown pipeline tag
- GLiNER2
How to use pooria/foxmind-small with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("pooria/foxmind-small") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) - Notebooks
- Google Colab
- Kaggle
Name the model foxmind; keep the GLiNER2 base model credit
Browse files
README.md
CHANGED
|
@@ -4,12 +4,15 @@ base_model: fastino/gliner2.5-small-v1
|
|
| 4 |
library_name: transformers.js
|
| 5 |
tags:
|
| 6 |
- gliner2
|
|
|
|
| 7 |
- onnx
|
| 8 |
---
|
| 9 |
|
| 10 |
-
#
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
| 13 |
|
| 14 |
The export keeps foxpilot's four inputs (`input_ids`, `attention_mask`, `word_positions`, `schema_positions`). It returns `cls_logits [1, L]` for classification and `span_probs [1, L, C]` with `span_bounds [1, C, 2]` for span extraction over the boundary candidate pool. `reference.json` holds the library's own results on 14 calls.
|
| 15 |
|
|
|
|
| 4 |
library_name: transformers.js
|
| 5 |
tags:
|
| 6 |
- gliner2
|
| 7 |
+
- foxpilot
|
| 8 |
- onnx
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# foxmind-small
|
| 12 |
|
| 13 |
+
foxmind-small is the small on-device model for the [foxpilot](https://github.com/pooriaarab/foxpilot) apps (PII Guard, Consent Shield and others). It is an ONNX export of GLiNER2.5 small.
|
| 14 |
+
|
| 15 |
+
Base model: [`fastino/gliner2.5-small-v1`](https://huggingface.co/fastino/gliner2.5-small-v1) (Apache-2.0, 74M parameters, English). It runs on-device in Firefox with ONNX Runtime Web.
|
| 16 |
|
| 17 |
The export keeps foxpilot's four inputs (`input_ids`, `attention_mask`, `word_positions`, `schema_positions`). It returns `cls_logits [1, L]` for classification and `span_probs [1, L, C]` with `span_bounds [1, C, 2]` for span extraction over the boundary candidate pool. `reference.json` holds the library's own results on 14 calls.
|
| 18 |
|