Ares-Realm-Studios/Trinity-Mini-Base
018
1{2 "architectures": [3 "AfmoeForCausalLM"4 ],5 "attention_dropout": 0.0,6 "dtype": "bfloat16",7 "global_attn_every_n_layers": 4,8 "head_dim": 128,9 "hidden_act": "silu",10 "hidden_size": 2048,11 "initializer_range": 0.02,12 "intermediate_size": 6144,13 "layer_types": [14 "sliding_attention",15 "sliding_attention",16 "sliding_attention",17 "full_attention",18 "sliding_attention",19 "sliding_attention",20 "sliding_attention",21 "full_attention",22 "sliding_attention",23 "sliding_attention",24 "sliding_attention",25 "full_attention",26 "sliding_attention",27 "sliding_attention",28 "sliding_attention",29 "full_attention",30 "sliding_attention",31 "sliding_attention",32 "sliding_attention",33 "full_attention",34 "sliding_attention",35 "sliding_attention",36 "sliding_attention",37 "full_attention",38 "sliding_attention",39 "sliding_attention",40 "sliding_attention",41 "full_attention",42 "sliding_attention",43 "sliding_attention",44 "sliding_attention",45 "full_attention"46 ],47 "load_balance_coeff": 0.001,48 "max_position_embeddings": 131072,49 "model_type": "afmoe",50 "moe_intermediate_size": 1024,51 "mup_enabled": true,52 "n_group": 1,53 "num_attention_heads": 32,54 "num_dense_layers": 2,55 "num_expert_groups": 1,56 "num_experts": 128,57 "num_experts_per_tok": 8,58 "num_hidden_layers": 32,59 "num_key_value_heads": 4,60 "num_limited_groups": 1,61 "num_shared_experts": 1,62 "rms_norm_eps": 1e-05,63 "rope_scaling": null,64 "rope_theta": 10000,65 "route_norm": true,66 "route_scale": 2.826,67 "score_func": "sigmoid",68 "sliding_window": 2048,69 "tie_word_embeddings": false,70 "topk_group": 1,71 "transformers_version": "4.57.0.dev0",72 "use_cache": true,73 "use_grouped_mm": true,74 "vocab_size": 200192,75 "auto_map": {76 "AutoConfig": "configuration_afmoe.AfmoeConfig",77 "AutoModelForCausalLM": "modeling_afmoe.AfmoeForCausalLM",78 "AutoModel": "modeling_afmoe.AfmoeModel"79 }80}