Token Classification
Transformers
Safetensors
Kabyle
belaid
kabyle
taqbaylit
berber
amazigh
punctuation-restoration
truecasing
asr-post-processing
low-resource
custom_code
Eval Results (legacy)
Instructions to use agbalu/Belaid-31M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use agbalu/Belaid-31M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="agbalu/Belaid-31M", trust_remote_code=True)# Load model directly from transformers import AutoModelForTokenClassification model = AutoModelForTokenClassification.from_pretrained("agbalu/Belaid-31M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source": "artifacts/runs/punctuation-v2/best.pt", | |
| "source_contents": [ | |
| "model", | |
| "optimizer", | |
| "rng", | |
| "state" | |
| ], | |
| "dropped_state": [ | |
| "optimizer", | |
| "rng" | |
| ], | |
| "dropped_tied": [ | |
| "encoder.classifier.decoder.weight" | |
| ], | |
| "dropped_derived": [ | |
| "encoder.transformer.attention_layers.0.position_indices", | |
| "encoder.transformer.attention_layers.1.position_indices", | |
| "encoder.transformer.attention_layers.10.position_indices", | |
| "encoder.transformer.attention_layers.11.position_indices", | |
| "encoder.transformer.attention_layers.2.position_indices", | |
| "encoder.transformer.attention_layers.3.position_indices", | |
| "encoder.transformer.attention_layers.4.position_indices", | |
| "encoder.transformer.attention_layers.5.position_indices", | |
| "encoder.transformer.attention_layers.6.position_indices", | |
| "encoder.transformer.attention_layers.7.position_indices", | |
| "encoder.transformer.attention_layers.8.position_indices", | |
| "encoder.transformer.attention_layers.9.position_indices" | |
| ], | |
| "tensors": 115, | |
| "parameters": 31423751, | |
| "files": [ | |
| { | |
| "name": "README.md", | |
| "bytes": 12931, | |
| "sha256": "8256a13d5b4f3ada9d65a79af9fb439940aeaaffcb6a50d31a4958270fd45b5d" | |
| }, | |
| { | |
| "name": "__init__.py", | |
| "bytes": 89, | |
| "sha256": "76c00392e334845477c36490abfa4a1adb85537a978bb3abb6262feda4f17e1e" | |
| }, | |
| { | |
| "name": "agbalu-tok-base-16k.model", | |
| "bytes": 260433, | |
| "sha256": "c8094fccd936d2e8954809bd9cf45331679e9550d2c7bbabe5c38c3bf365dc4e" | |
| }, | |
| { | |
| "name": "config.json", | |
| "bytes": 852, | |
| "sha256": "f27945c4243cd4a9f1ade7ee80c5a07291176755797aefd8e215532090cec234" | |
| }, | |
| { | |
| "name": "configuration_belaid.py", | |
| "bytes": 2465, | |
| "sha256": "672a6ad80d73382528d450ee29e9c3938b3c405fea4949e4ef962b0067efecf9" | |
| }, | |
| { | |
| "name": "model.safetensors", | |
| "bytes": 125708716, | |
| "sha256": "6ac511717b137eb7313f2d3f978e7bbeffc08997ccac9bf43a58ed18a77d0f1f" | |
| }, | |
| { | |
| "name": "modeling_belaid.py", | |
| "bytes": 17876, | |
| "sha256": "0aa17d3a6f2771033520444d7a24af2da50509df6451b0df1f3d3dc491da3828" | |
| }, | |
| { | |
| "name": "tokenizer.json", | |
| "bytes": 1020068, | |
| "sha256": "852cfe5f6aa50ae17ccc23b1c119868db78f9c2cb46fb40915fb7a5bbe482e21" | |
| }, | |
| { | |
| "name": "tokenizer_config.json", | |
| "bytes": 221, | |
| "sha256": "cc21f3d5467039f7a2dc24c40886f738eefd3f9c0112dcae2a19c7517c2ed906" | |
| } | |
| ] | |
| } | |