nitsanluke's picture
initial commit
d11cf3c
{
"architectures": [
"AprielHForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_apriel_h.AprielHConfig",
"AutoModel": "modeling_apriel_h.AprielHModel",
"AutoModelForCausalLM": "modeling_apriel_h.AprielHForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"hybrid_block_layout": [
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"t",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"t",
"m2",
"t",
"t",
"m2",
"m2",
"m2",
"m2",
"t",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"m2",
"t",
"m2"
],
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 65536,
"model_type": "apriel_h",
"num_attention_heads": 32,
"num_hidden_layers": 50,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"rope_type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"ssm_cfg": {
"activation": "silu",
"bias": false,
"chunk_size": 128,
"conv_bias": true,
"d_conv": 4,
"d_inner": 4096,
"d_state": 16,
"d_xb": 1024,
"dt_init": "random",
"dt_init_floor": 0.0001,
"dt_max": 0.1,
"dt_min": 0.001,
"dt_rank": 320,
"dt_scale": 1.0,
"expand": 1,
"n_qk_heads": 32,
"n_v_heads": 32
},
"tie_word_embeddings": false,
"transformers_version": "4.53.2",
"use_cache": true,
"vocab_size": 131072
}