| { |
| "framework": "pytorch", |
| "task": "ner", |
| "model_class": "DistilBertForTokenClassification", |
| "state_dict_keys": [ |
| "distilbert.embeddings.word_embeddings.weight", |
| "distilbert.embeddings.position_embeddings.weight", |
| "distilbert.embeddings.LayerNorm.weight", |
| "distilbert.embeddings.LayerNorm.bias", |
| "distilbert.transformer.layer.0.attention.q_lin.weight", |
| "distilbert.transformer.layer.0.attention.q_lin.bias", |
| "distilbert.transformer.layer.0.attention.k_lin.weight", |
| "distilbert.transformer.layer.0.attention.k_lin.bias", |
| "distilbert.transformer.layer.0.attention.v_lin.weight", |
| "distilbert.transformer.layer.0.attention.v_lin.bias", |
| "distilbert.transformer.layer.0.attention.out_lin.weight", |
| "distilbert.transformer.layer.0.attention.out_lin.bias", |
| "distilbert.transformer.layer.0.sa_layer_norm.weight", |
| "distilbert.transformer.layer.0.sa_layer_norm.bias", |
| "distilbert.transformer.layer.0.ffn.lin1.weight", |
| "distilbert.transformer.layer.0.ffn.lin1.bias", |
| "distilbert.transformer.layer.0.ffn.lin2.weight", |
| "distilbert.transformer.layer.0.ffn.lin2.bias", |
| "distilbert.transformer.layer.0.output_layer_norm.weight", |
| "distilbert.transformer.layer.0.output_layer_norm.bias", |
| "distilbert.transformer.layer.1.attention.q_lin.weight", |
| "distilbert.transformer.layer.1.attention.q_lin.bias", |
| "distilbert.transformer.layer.1.attention.k_lin.weight", |
| "distilbert.transformer.layer.1.attention.k_lin.bias", |
| "distilbert.transformer.layer.1.attention.v_lin.weight", |
| "distilbert.transformer.layer.1.attention.v_lin.bias", |
| "distilbert.transformer.layer.1.attention.out_lin.weight", |
| "distilbert.transformer.layer.1.attention.out_lin.bias", |
| "distilbert.transformer.layer.1.sa_layer_norm.weight", |
| "distilbert.transformer.layer.1.sa_layer_norm.bias", |
| "distilbert.transformer.layer.1.ffn.lin1.weight", |
| "distilbert.transformer.layer.1.ffn.lin1.bias", |
| "distilbert.transformer.layer.1.ffn.lin2.weight", |
| "distilbert.transformer.layer.1.ffn.lin2.bias", |
| "distilbert.transformer.layer.1.output_layer_norm.weight", |
| "distilbert.transformer.layer.1.output_layer_norm.bias", |
| "distilbert.transformer.layer.2.attention.q_lin.weight", |
| "distilbert.transformer.layer.2.attention.q_lin.bias", |
| "distilbert.transformer.layer.2.attention.k_lin.weight", |
| "distilbert.transformer.layer.2.attention.k_lin.bias", |
| "distilbert.transformer.layer.2.attention.v_lin.weight", |
| "distilbert.transformer.layer.2.attention.v_lin.bias", |
| "distilbert.transformer.layer.2.attention.out_lin.weight", |
| "distilbert.transformer.layer.2.attention.out_lin.bias", |
| "distilbert.transformer.layer.2.sa_layer_norm.weight", |
| "distilbert.transformer.layer.2.sa_layer_norm.bias", |
| "distilbert.transformer.layer.2.ffn.lin1.weight", |
| "distilbert.transformer.layer.2.ffn.lin1.bias", |
| "distilbert.transformer.layer.2.ffn.lin2.weight", |
| "distilbert.transformer.layer.2.ffn.lin2.bias", |
| "distilbert.transformer.layer.2.output_layer_norm.weight", |
| "distilbert.transformer.layer.2.output_layer_norm.bias", |
| "distilbert.transformer.layer.3.attention.q_lin.weight", |
| "distilbert.transformer.layer.3.attention.q_lin.bias", |
| "distilbert.transformer.layer.3.attention.k_lin.weight", |
| "distilbert.transformer.layer.3.attention.k_lin.bias", |
| "distilbert.transformer.layer.3.attention.v_lin.weight", |
| "distilbert.transformer.layer.3.attention.v_lin.bias", |
| "distilbert.transformer.layer.3.attention.out_lin.weight", |
| "distilbert.transformer.layer.3.attention.out_lin.bias", |
| "distilbert.transformer.layer.3.sa_layer_norm.weight", |
| "distilbert.transformer.layer.3.sa_layer_norm.bias", |
| "distilbert.transformer.layer.3.ffn.lin1.weight", |
| "distilbert.transformer.layer.3.ffn.lin1.bias", |
| "distilbert.transformer.layer.3.ffn.lin2.weight", |
| "distilbert.transformer.layer.3.ffn.lin2.bias", |
| "distilbert.transformer.layer.3.output_layer_norm.weight", |
| "distilbert.transformer.layer.3.output_layer_norm.bias", |
| "distilbert.transformer.layer.4.attention.q_lin.weight", |
| "distilbert.transformer.layer.4.attention.q_lin.bias", |
| "distilbert.transformer.layer.4.attention.k_lin.weight", |
| "distilbert.transformer.layer.4.attention.k_lin.bias", |
| "distilbert.transformer.layer.4.attention.v_lin.weight", |
| "distilbert.transformer.layer.4.attention.v_lin.bias", |
| "distilbert.transformer.layer.4.attention.out_lin.weight", |
| "distilbert.transformer.layer.4.attention.out_lin.bias", |
| "distilbert.transformer.layer.4.sa_layer_norm.weight", |
| "distilbert.transformer.layer.4.sa_layer_norm.bias", |
| "distilbert.transformer.layer.4.ffn.lin1.weight", |
| "distilbert.transformer.layer.4.ffn.lin1.bias", |
| "distilbert.transformer.layer.4.ffn.lin2.weight", |
| "distilbert.transformer.layer.4.ffn.lin2.bias", |
| "distilbert.transformer.layer.4.output_layer_norm.weight", |
| "distilbert.transformer.layer.4.output_layer_norm.bias", |
| "distilbert.transformer.layer.5.attention.q_lin.weight", |
| "distilbert.transformer.layer.5.attention.q_lin.bias", |
| "distilbert.transformer.layer.5.attention.k_lin.weight", |
| "distilbert.transformer.layer.5.attention.k_lin.bias", |
| "distilbert.transformer.layer.5.attention.v_lin.weight", |
| "distilbert.transformer.layer.5.attention.v_lin.bias", |
| "distilbert.transformer.layer.5.attention.out_lin.weight", |
| "distilbert.transformer.layer.5.attention.out_lin.bias", |
| "distilbert.transformer.layer.5.sa_layer_norm.weight", |
| "distilbert.transformer.layer.5.sa_layer_norm.bias", |
| "distilbert.transformer.layer.5.ffn.lin1.weight", |
| "distilbert.transformer.layer.5.ffn.lin1.bias", |
| "distilbert.transformer.layer.5.ffn.lin2.weight", |
| "distilbert.transformer.layer.5.ffn.lin2.bias", |
| "distilbert.transformer.layer.5.output_layer_norm.weight", |
| "distilbert.transformer.layer.5.output_layer_norm.bias", |
| "classifier.weight", |
| "classifier.bias" |
| ] |
| } |
