Commit
•
99e1310
1
Parent(s):
3d96e5f
update model card
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
- token classification
|
| 7 |
license: agpl-3.0
|
| 8 |
datasets:
|
| 9 |
-
- EMBO/sd-
|
| 10 |
metrics:
|
| 11 |
-
|
| 12 |
---
|
|
@@ -15,7 +15,7 @@ metrics:
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
| 18 |
-
This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of English scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-nlp](https://huggingface.co/datasets/EMBO/sd-
|
| 19 |
|
| 20 |
|
| 21 |
## Intended uses & limitations
|
|
@@ -43,17 +43,17 @@ The model must be used with the `roberta-base` tokenizer.
|
|
| 43 |
|
| 44 |
## Training data
|
| 45 |
|
| 46 |
-
The model was trained for token classification using the [EMBO/sd-
|
| 47 |
|
| 48 |
## Training procedure
|
| 49 |
|
| 50 |
-
The training was run on
|
| 51 |
|
| 52 |
Training code is available at https://github.com/source-data/soda-roberta
|
| 53 |
|
| 54 |
- Model fine-tuned: EMBO/bio-lm
|
| 55 |
- Tokenizer vocab size: 50265
|
| 56 |
-
- Training data: EMBO/sd-
|
| 57 |
- Dataset configuration: NER
|
| 58 |
- Training with 48771 examples.
|
| 59 |
- Evaluating on 13801 examples.
|
| 6 |
- token classification
|
| 7 |
license: agpl-3.0
|
| 8 |
datasets:
|
| 9 |
+
- EMBO/sd-panels
|
| 10 |
metrics:
|
| 11 |
-
|
| 12 |
---
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
| 18 |
+
This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of English scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-nlp](https://huggingface.co/datasets/EMBO/sd-panels) dataset with the `NER` configuration to perform Named Entity Recognition of bioentities.
|
| 19 |
|
| 20 |
|
| 21 |
## Intended uses & limitations
|
| 43 |
|
| 44 |
## Training data
|
| 45 |
|
| 46 |
+
The model was trained for token classification using the [EMBO/sd-panels dataset](https://huggingface.co/datasets/EMBO/sd-panels) dataset which includes manually annotated examples.
|
| 47 |
|
| 48 |
## Training procedure
|
| 49 |
|
| 50 |
+
The training was run on an NVIDIA DGX Station with 4XTesla V100 GPUs.
|
| 51 |
|
| 52 |
Training code is available at https://github.com/source-data/soda-roberta
|
| 53 |
|
| 54 |
- Model fine-tuned: EMBO/bio-lm
|
| 55 |
- Tokenizer vocab size: 50265
|
| 56 |
+
- Training data: EMBO/sd-panels
|
| 57 |
- Dataset configuration: NER
|
| 58 |
- Training with 48771 examples.
|
| 59 |
- Evaluating on 13801 examples.
|