Update README.md
Browse files
README.md
CHANGED
|
@@ -23,12 +23,12 @@ GLiNER is a Named Entity Recognition (NER) model capable of identifying any enti
|
|
| 23 |
|
| 24 |
GLiNER-bi-V2 Models:
|
| 25 |
|
| 26 |
-
| Model name
|
| 27 |
-
|
| 28 |
-
| gliner-bi-edge-v2.0
|
| 29 |
-
| gliner-bi-small-v2.0
|
| 30 |
-
| gliner-bi-base-v2.0
|
| 31 |
-
| gliner-bi-large-v2.0
|
| 32 |
|
| 33 |
Such architecture brings several advantages over uni-encoder GLiNER:
|
| 34 |
* An unlimited amount of entities can be recognized at a single time;
|
|
|
|
| 23 |
|
| 24 |
GLiNER-bi-V2 Models:
|
| 25 |
|
| 26 |
+
| Model name | Params | Encoder | Labels Encoder | Avg. CrossNER Benchmark | Avg. Inference Speed (H100, examples/s) | Avg. Inference Speed (H100, examples/s, pre-computed labels) |
|
| 27 |
+
|-------------------------------------------------------------------------------------------------|--------|------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------|-------------------------|------------------------------------------|----------------------------------------------------------|
|
| 28 |
+
| [gliner-bi-edge-v2.0](https://huggingface.co/knowledgator/gliner-bi-edge-v2.0) | 60 M | [ettin-encoder-32m](https://huggingface.co/jhu-clsp/ettin-encoder-32m) | [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | 54.0% | 13.64 | 24.62 |
|
| 29 |
+
| [gliner-bi-small-v2.0](https://huggingface.co/knowledgator/gliner-bi-small-v2.0) | 108 M | [ettin-encoder-68m](https://huggingface.co/jhu-clsp/ettin-encoder-68m) | [all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) | 57.2% | 7.99 | 15.22 |
|
| 30 |
+
| [gliner-bi-base-v2.0](https://huggingface.co/knowledgator/gliner-bi-base-v2.0) | 194 M | [ettin-encoder-150m](https://huggingface.co/jhu-clsp/ettin-encoder-150m) | [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 60.3% | 5.91 | 9.51 |
|
| 31 |
+
| [gliner-bi-large-v2.0](https://huggingface.co/knowledgator/gliner-bi-large-v2.0) | 530 M | [ettin-encoder-400m](https://huggingface.co/jhu-clsp/ettin-encoder-400m) | [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 61.5% | 2.68 | 3.60 |
|
| 32 |
|
| 33 |
Such architecture brings several advantages over uni-encoder GLiNER:
|
| 34 |
* An unlimited amount of entities can be recognized at a single time;
|