LOINC_CROSS_ENCODER / config.json
champ7's picture
Checkpoint Step 10000
4267197 verified
{
"_sliding_window_pattern": 6,
"architectures": [
"Gemma3TextForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"dtype": "float32",
"eos_token_id": 1,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 768,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"LABEL_0": 0
},
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 2048,
"model_type": "gemma3_text",
"num_attention_heads": 3,
"num_hidden_layers": 24,
"num_key_value_heads": 1,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sentence_transformers": {
"activation_fn": "torch.nn.modules.activation.Sigmoid",
"version": "5.3.0"
},
"sliding_window": 257,
"tie_word_embeddings": true,
"transformers_version": "5.5.0",
"use_bidirectional_attention": true,
"use_cache": true,
"vocab_size": 262144
}