Add model description
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ tags:
|
|
| 4 |
language:
|
| 5 |
- fa
|
| 6 |
---
|
|
|
|
|
|
|
| 7 |
| Feature | Description |
|
| 8 |
| --- | --- |
|
| 9 |
| **Name** | `fa_floret` |
|
|
@@ -14,4 +16,4 @@ language:
|
|
| 14 |
| **Vectors** | -1 keys, 50000 unique vectors (300 dimensions) |
|
| 15 |
| **Sources** | n/a |
|
| 16 |
| **License** | n/a |
|
| 17 |
-
| **Author** | [n/a]() |
|
|
|
|
| 4 |
language:
|
| 5 |
- fa
|
| 6 |
---
|
| 7 |
+
Floret vectors for Persian: fastText-style subwords hashed into a fixed 50,000-row Bloom table (300 dimensions), the same table shape as `fa_floret_400k`, retrained on the full Persian Wikipedia dump instead of a 400,000-document sample. Vectors-only package, no pipeline components — load with `spacy.load` or unpack and point `--paths.vectors` at it to train against.
|
| 8 |
+
|
| 9 |
| Feature | Description |
|
| 10 |
| --- | --- |
|
| 11 |
| **Name** | `fa_floret` |
|
|
|
|
| 16 |
| **Vectors** | -1 keys, 50000 unique vectors (300 dimensions) |
|
| 17 |
| **Sources** | n/a |
|
| 18 |
| **License** | n/a |
|
| 19 |
+
| **Author** | [n/a]() |
|