{ "_name_or_path": "ScrapeGoat-v1", "model_type": "scrapegoat", "vocab_size": 248320, "hidden_size": 4096, "num_hidden_layers": 81, "hidden_act": "silu", "max_position_embeddings": 262144, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "pad_token_id": 0, "bos_token_id": 1, "eos_token_id": 2, "tie_word_embeddings": false, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "track_a_num_attention_heads": 32, "track_a_num_key_value_heads": 2, "track_a_head_dim": 256, "track_a_num_experts": 512, "track_a_moe_intermediate_size": 1024, "track_b_num_attention_heads": 64, "track_b_num_key_value_heads": 8, "track_b_head_dim": 128, "track_b_num_experts": 192, "num_experts": 704, "track_b_moe_intermediate_size": 1536, "track_b_intermediate_size": 13312, "num_experts_per_tok": 8, "output_router_logits": false, "router_aux_loss_coef": 0.001, "kda_head_dim": 256, "kda_conv_kernel": 3, "kda_gqa_layers": [ 0, 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44, 48, 52, 56, 60, 64, 68, 72, 76, 80 ], "quantile_balancing": true, "qb_iterations": 5, "attn_residual": false, "attn_res_blocks": 8, "stable_moe_stage": 1, "mom_enabled": true, "mom_num_memories": 4, "mom_active_memories": 2, "mom_shared_memory": true, "mom_load_balancing": true, "stable_moe_r3": false, "stable_moe_r3_cache": true, "dspark_block_size": 6, "dspark_noise_token_id": 0, "dspark_target_layer_ids": [], "dspark_markov_rank": 256, "num_attention_heads": 32, "num_key_value_heads": 8, "architectures": [ "ScrapeGoatForCausalLM" ], "return_dict": true }