{ "A_init_range": [ 1, 16 ], "architectures": [ "LogosForCausalLM" ], "attention_sink": true, "attn_pattern": null, "auto_map": { "AutoConfig": "configuration_logos.LogosConfig", "AutoModelForCausalLM": "modeling_logos.LogosForCausalLM", "AutoTokenizer": "tokenization_logos.LogosTokenizer" }, "bias_update_rate": 0.02, "block_residual_isolate_softmax": false, "body_attn_pattern": "hca,csa,kda,swa,csa,kda,csa,hca,kda,swa,csa,kda,csa,csa,kda,swa,hca,kda", "bos_token_id": 100257, "capacity_factor": 2.0, "chunk_size": 128, "ckpt_granularity": "per-block", "compressed_head_dim": null, "compressed_query_dim": null, "compressed_rope": false, "conv_size": 4, "csa_compression": 4, "csa_indexer_dim": 32, "csa_indexer_heads": 4, "csa_indexer_loss_weight": 1.0, "csa_top_k": 64, "d_ff": 2730, "d_model": 1024, "dtype": "bfloat16", "entry_attn_pattern": "hca,kda", "entry_top_k": 12, "eos_token_id": 100257, "exit_attn_pattern": "csa,swa", "exit_top_k": 12, "expand": 2, "expert_d_ff": 832, "gradient_checkpointing": true, "hca_compression": 128, "head_dim": 64, "indexer_rope": false, "lm_head_chunk_size": 4096, "max_seq_len": 4096, "model_max_length": 4096, "model_type": "logos", "moe_aux_loss_decay_steps": 8000, "moe_aux_loss_weight": 0.001, "moe_diversity_factor": 0.0, "norm_eps": 1e-06, "num_body_layers": 6, "num_entry_layers": 2, "num_exit_layers": 2, "num_heads": 16, "num_layers": 10, "num_loops": 3, "num_shared_experts": 2, "num_sparse_experts": 32, "pad_token_id": 100257, "partial_rope_dim": null, "qk_norm": true, "rope_base": 10000.0, "router_bias_clip": 1.0, "router_bias_error_clip": 1.0, "router_init_std": 0.002, "router_logit_noise_decay_steps": 8000, "router_logit_noise_std": 0.08, "swa_every": 4, "swa_offset": 3, "swa_window": 256, "tie_word_embeddings": true, "tokenizer_encoding": "cl100k_base", "top_k": 6, "transformers_version": "5.5.4", "use_moe": true, "vocab_size": 100277 }