zerank-2 / config.json
Tom Aarsen
Update model type to remove warning
e2b7a7c
raw
history blame
1.78 kB
{
"architectures": [
"ZeroEntropyForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "modeling_zeranker.ZeroEntropyConfig",
"AutoModelForSequenceClassification": "modeling_zeranker.ZeroEntropyForSequenceClassification"
},
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "zeroentropy",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"num_labels": 1,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}