Token Classification
Transformers
Safetensors
deberta-v2
ner
named-entity-recognition
multinerd
mdeberta-v3
mdeberta
deberta
lora
multilingual
multi-domain-ner
information-extraction
nlp
sequence-labeling
bio-tagging
entity-extraction
transformer
Instructions to use Rishabh157/multinerd-multilingual-ner-mdeberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rishabh157/multinerd-multilingual-ner-mdeberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Rishabh157/multinerd-multilingual-ner-mdeberta")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Rishabh157/multinerd-multilingual-ner-mdeberta") model = AutoModelForTokenClassification.from_pretrained("Rishabh157/multinerd-multilingual-ner-mdeberta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from Rishabh157/multinerd-multilingual-ner-mdeberta: direct link, hf CLI and curl.
- Browser
- Download file 1.96 kB
-
https://huggingface.co/Rishabh157/multinerd-multilingual-ner-mdeberta/resolve/main/eval_results.json
- Command line
-
hf download hf://Rishabh157/multinerd-multilingual-ner-mdeberta/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/Rishabh157/multinerd-multilingual-ner-mdeberta/resolve/main/eval_results.json
1.96 kB
| [ | |
| { | |
| "eval_loss": 0.03150395303964615, | |
| "eval_precision": 0.8543351681270127, | |
| "eval_recall": 0.7158848007781399, | |
| "eval_f1": 0.7790062204581586, | |
| "eval_accuracy": 0.9604577600987738, | |
| "eval_runtime": 619.2061, | |
| "eval_samples_per_second": 270.346, | |
| "eval_steps_per_second": 16.897, | |
| "epoch": 1.0, | |
| "step": 83700 | |
| }, | |
| { | |
| "eval_loss": 0.02791716903448105, | |
| "eval_precision": 0.8849638055842813, | |
| "eval_recall": 0.7551800821282755, | |
| "eval_f1": 0.8149370849575276, | |
| "eval_accuracy": 0.967312468759109, | |
| "eval_runtime": 909.8023, | |
| "eval_samples_per_second": 183.996, | |
| "eval_steps_per_second": 11.5, | |
| "epoch": 2.0, | |
| "step": 167400 | |
| }, | |
| { | |
| "eval_loss": 0.025783492252230644, | |
| "eval_precision": 0.8806553680535351, | |
| "eval_recall": 0.7597689112708703, | |
| "eval_f1": 0.8157579458241655, | |
| "eval_accuracy": 0.9685670918568089, | |
| "eval_runtime": 911.3921, | |
| "eval_samples_per_second": 183.675, | |
| "eval_steps_per_second": 11.48, | |
| "epoch": 3.0, | |
| "step": 251100 | |
| }, | |
| { | |
| "eval_loss": 0.02454463206231594, | |
| "eval_precision": 0.89487843442792, | |
| "eval_recall": 0.7658167527562391, | |
| "eval_f1": 0.8253325499511796, | |
| "eval_accuracy": 0.9699400285726002, | |
| "eval_runtime": 920.4105, | |
| "eval_samples_per_second": 181.875, | |
| "eval_steps_per_second": 11.368, | |
| "epoch": 4.0, | |
| "step": 334800 | |
| }, | |
| { | |
| "eval_loss": 0.024302557110786438, | |
| "eval_precision": 0.8981254759266606, | |
| "eval_recall": 0.7725195809653799, | |
| "eval_f1": 0.8306007472442207, | |
| "eval_accuracy": 0.9707923299525748, | |
| "eval_runtime": 910.8792, | |
| "eval_samples_per_second": 183.778, | |
| "eval_steps_per_second": 11.487, | |
| "epoch": 5.0, | |
| "step": 418500 | |
| } | |
| ] |