Indivec / config.json
Sailesh Panda
Experimenting
9a26c21
{
"attention_dropout": 0.0,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_types": [
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 16384,
"max_window_layers": 28,
"model_type": "hinvec",
"num_attention_heads": 16,
"num_hidden_layers": 12,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": 10,
"tie_word_embeddings": false,
"transformers_version": "4.56.2",
"use_cache": true,
"use_sliding_window": true,
"vocab_size": 256002,
"pad_token_id": 3,
"bos_token_id": 256000,
"auto_map": {
"AutoConfig": "Sailesh97/Hinvec2--configuration_hinvec.HinvecConfig",
"AutoModel": "Sailesh97/Hinvec2--modeling_hinvec.HinvecModel"}
}