Updated Readme
Browse files
README.md
CHANGED
|
@@ -103,8 +103,6 @@ This is an [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NL
|
|
| 103 |
|
| 104 |
## Limitations
|
| 105 |
|
| 106 |
-
Whilst this model natively supports inputs up to 8192, all of our evaluations are on sentence level so there are no guarantees on it's longer text embedding capabilities of Historical Luxembourgish.
|
| 107 |
-
|
| 108 |
We also release a model that performs better (18pp) on ParaLUX. If finding monolingual exact matches within adversarial collections is of at-most importance, please use [histlux-paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/impresso-project/histlux-paraphrase-multilingual-mpnet-base-v2)
|
| 109 |
|
| 110 |
### Model Description
|
|
@@ -114,7 +112,7 @@ We also release a model that performs better (18pp) on ParaLUX. If finding monol
|
|
| 114 |
- **Output Dimensionality:** 768 dimensions
|
| 115 |
- **Similarity Function:** Cosine Similarity
|
| 116 |
- **Training Dataset:**
|
| 117 |
-
- LB-EN (
|
| 118 |
|
| 119 |
|
| 120 |
## Usage (Sentence-Transformers)
|
|
|
|
| 103 |
|
| 104 |
## Limitations
|
| 105 |
|
|
|
|
|
|
|
| 106 |
We also release a model that performs better (18pp) on ParaLUX. If finding monolingual exact matches within adversarial collections is of at-most importance, please use [histlux-paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/impresso-project/histlux-paraphrase-multilingual-mpnet-base-v2)
|
| 107 |
|
| 108 |
### Model Description
|
|
|
|
| 112 |
- **Output Dimensionality:** 768 dimensions
|
| 113 |
- **Similarity Function:** Cosine Similarity
|
| 114 |
- **Training Dataset:**
|
| 115 |
+
- LB-EN (Historical, Modern)
|
| 116 |
|
| 117 |
|
| 118 |
## Usage (Sentence-Transformers)
|