Instructions to use BEE-spoke-data/neobert-100k-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BEE-spoke-data/neobert-100k-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="BEE-spoke-data/neobert-100k-test", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("BEE-spoke-data/neobert-100k-test", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "NeoBERTLMHead" | |
| ], | |
| "model_type": "neobert", | |
| "auto_map": { | |
| "AutoConfig": "model.NeoBERTConfig", | |
| "AutoModel": "model.NeoBERT", | |
| "AutoModelForMaskedLM": "model.NeoBERTLMHead", | |
| "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification" | |
| }, | |
| "hidden_size": 768, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 12, | |
| "intermediate_size": 3072, | |
| "vocab_size": 31999, | |
| "max_length": 4096, | |
| "embedding_init_range": 0.02, | |
| "decoder_init_range": 0.02, | |
| "norm_eps": 1e-05, | |
| "pad_token_id": 0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.0" | |
| } |