active_expert_width: null
active_num_experts: null
attention_dropout: 0.0
attention_type: gqa
causal_context_fusion_size: 0
causal_context_gate_init: 1.0
causal_contextual_mix_init: 0.0
causal_conv_dilation_cycle: 8
causal_conv_kernel_size: 4
causal_delta_chunk_size: 512
causal_delta_collision_normalized: false
causal_delta_lexical_forge: false
causal_delta_lexical_values: false
causal_delta_occurrence_address: false
causal_delta_timescales: 1
causal_stable_delta: false
causal_state_rank: 16
collect_moe_telemetry: false
expert_initialization: gpt_normal
extra_config: {}
hash_channel_scale_init: 0.0
hash_pair_gate_init: 0.5
hidden_act: silu
hidden_size: 896
initializer_range: 0.02
intermediate_size: 256
is_causal: true
learn_hash_channel_modulation: false
learn_hash_pair_gates: false
lexical_gqa_gate_init: 0.0
lexical_gqa_rank: 16
lexical_gqa_use_token_code: true
lexical_key_gate_init: 0.05
lexical_object_gate_init: 0.1
lexical_object_rank: 16
lexical_zipf_alpha: 0.25
lexical_zipf_floor: 0.1
lexical_zipf_mode: uniform
lexical_zipf_path: null
lexical_zipf_permutation_seed: 1729
lsh_bits: 0
lsh_from_layer: 0
lsh_routing: false
lsh_threshold_mode: zero
max_position_embeddings: 2048
micro_expert_gate_init: 0.1
micro_expert_width: 16
micro_num_experts: 4
mlp_type: tr_hash_engine
mup_base_width: 256
norm_eps: 1.0e-06
norm_type: rmsnorm
num_attention_heads: 14
num_experts: 4
num_hidden_layers: 16
num_key_value_heads: 2
rope_fraction: 1.0
rope_theta: 10000.0
rope_type: standard
route_hash_count: 2
routed_gate_init: 1.0
routed_output_scale: 2.0
routed_output_scale_first_layer: null
routed_output_scale_last_layer: null
routing_strategy: token_id_multi_hash
shared_expert: true
shared_expert_chunk_tokens: 0
shared_gate_init: 1.0
shared_intermediate_size: 3072
shared_output_scale: 1.0
shared_output_scale_first_layer: null
shared_output_scale_last_layer: null
sliding_window: null
static_expert_capacity: false
tie_lexical_object_embeddings: false
tie_word_embeddings: true
token_frequencies: null
top_k: 2
top_k_primary_weight: 0.5
tr_mha_adapter_gate_init: 0.1
tr_mha_adapter_rank: 8
tr_mha_id_other_logit: -2.0
tr_mha_id_primary_logit: 2.0
tr_mha_id_secondary_logit: 1.0
tr_mha_num_experts: 4
tr_mha_targets: qv
tr_mha_top_k: 2
tr_mha_verifier_gate_init: 0.1
tr_mha_verifier_temperature: 1.0
use_cache: true
use_cggr: auto
use_custom_kernels: auto
use_mup_attn_scale: false
use_mup_init: false
use_mup_output_mult: false
use_qk_norm: true
use_sdpa: true
use_shared_routed_gates: false
vocab_size: 32000