tartuNLP/EstBERT_NER_v2 ↗
- source model id
- HuggingFace/tartunlp-estbert-ner-v2@2
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- cc-by-4.0
- architecture
- input_modalities
- output_modalities
- capabilities
`tartuNLP/EstBERT_NER_v2` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/tartuNLP/EstBERT_NER_v2) - [`token-classification` Task on Hugging Face](https://hug…
azureFoundry/HuggingFace/tartunlp-estbert-ner-v2@2
`tartuNLP/EstBERT_NER_v2` powered by Hugging Face Inference Toolkit
- [Original Model Card](https://huggingface.co/tartuNLP/EstBERT_NER_v2) - [`token-classification` Task on Hugging Face](https://huggingface.co/tasks/token-classification)
### Send Request
You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.
```bash curl <AZUREML_ENDPOINT_URL> \ -X POST \ -H "Authorization: Bearer <AZUREML_TOKEN>" \ -H "Content-Type: application/json" \ -d '{"inputs":"My name is Sarah Jessica Parker but you can call me Jessica"}' ```
### Supported Parameters
- **inputs** (string): The input text data - **parameters** (object): - **ignore_labels** (string[]): A list of labels to ignore - **stride** (integer): The number of overlapping tokens between chunks when splitting the input text. - **aggregation_strategy** (string): One of the following: - **none**: Do not aggregate tokens - **simple**: Group consecutive tokens with the same label in a single entity. - **first**: Similar to "simple", also preserves word integrity (use the label predicted for the first token in a word). - **average**: Similar to "simple", also preserves word integrity (uses the label with the highest score, averaged across the word’s tokens). - **max**: Similar to "simple", also preserves word integrity (uses the label with the highest score across the word’s tokens).
Check the full API Specification at [the Hugging Face Inference documentation](https://huggingface.co/docs/inference-providers/tasks/token-classification#api-specification).
1–1 / 1
1–4 / 4
Hugging Face · tartuNLP/EstBERT_NER_v2 ↗
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.