VISTA-24M / config.json
AwakeningOS's picture
Release VISTA-24M: model, architecture diagrams, training recipe and evaluation evidence
9287d39 verified
Raw History Blame Contribute Delete
1.07 kB
{
"auto_map": {
"AutoConfig": "configuration_dense.ModernDenseConfig",
"AutoModel": "modeling_dense.ModernDenseModel",
"AutoModelForCausalLM": "modeling_dense.ModernDenseForCausalLM"
},
"bos_token_id": 1,
"dense_config": {
"arm": "mha_gated_ffn_router",
"backend": "sdpa",
"dropout": 0.0,
"eps": 1e-06,
"head_dim": 32,
"hidden": 896,
"kv_heads": 8,
"layers": 7,
"q_heads": 8,
"seed": 20260907,
"value_variance": true,
"variance_delivery": "full_width_direct",
"vocab": 16384,
"width": 256
},
"eos_token_id": 2,
"hidden_size": 256,
"model_type": "modern_dense_mha_gated_ffn_router",
"pad_token_id": 3,
"tie_word_embeddings": false,
"transformers_version": "5.14.1",
"vocab_size": 16384,
"architectures": [
"ModernDenseForCausalLM"
],
"intermediate_size": 896,
"num_hidden_layers": 7,
"num_attention_heads": 8,
"num_key_value_heads": 8,
"head_dim": 32,
"max_position_embeddings": 512,
"rope_theta": 10000.0,
"rms_norm_eps": 1e-06,
"use_cache": false
}