File size: 1,293 Bytes
2fe4bd1 3fb4a31 2fe4bd1 8a64a35 2fe4bd1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | {
"model_type": "neuroblast",
"architectures": [
"NeuroBLASTForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_neuroblast.NeuroBLASTConfig",
"AutoModelForCausalLM": "modeling_neuroblast.NeuroBLASTForCausalLM"
},
"association_cortex_hidden_size": 1024,
"association_gradient_scale": 0.8,
"cross_attention_gradient_scale": 0.8,
"dropout": 0.0,
"eos_token_id": [
2,
32009
],
"gradient_scaling_enabled": true,
"hidden_size": 1536,
"intermediate_size": 3072,
"kv_dim": 12288,
"max_position_embeddings": 131072,
"motor_cortex_hidden_size": 1024,
"norm_topk_prob": true,
"num_association_cortex_layers": 3,
"num_experts": null,
"num_experts_per_tok": 4,
"num_heads": 32,
"num_motor_cortex_layers": 3,
"num_sensory_cortex_layers": 3,
"pad_token_id": 32000,
"precomputed_total_layers": 18,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"sensory_cortex_hidden_size": 1024,
"sensory_gradient_scale": 0.95,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.2",
"use_zero_memory": true,
"vocab_size": 32024,
"zero_memory_layers": [
15
]
}
|