{ "activation_func": "swiglu", "activation_func_fp8_input_store": false, "add_bias_linear": false, "architectures": [ "ZayaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bias_activation_fusion": true, "bos_token_id": 2, "cca": true, "cca_num_q_heads": 8, "cca_time0": 2, "cca_time1": 2, "clamp_temp": false, "dtype": "bfloat16", "eos_token_id": 106, "ffn_hidden_size": 4096, "gated_linear_unit": true, "hidden_size": 2048, "kv_channels": 128, "lm_head_bias": false, "mamba_cache_dtype": "float32", "max_position_embeddings": 131072, "model_type": "zaya", "moe_router_topk": 1, "norm_epsilon": 1e-05, "normalization": "RMSNorm", "num_attention_heads": 16, "num_experts": 16, "num_hidden_layers": 80, "num_key_value_heads": 2, "num_query_groups": 2, "pad_token_id": 0, "partial_rotary_factor": 0.5, "quantization_config": { "_load_in_4bit": false, "_load_in_8bit": true, "bnb_4bit_compute_dtype": "float32", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "residual_in_fp32": true, "rope_scaling": false, "rope_theta": 5000000, "scale_residual_merge": true, "sliding_window": null, "swa_layers": null, "swa_rotary_base": null, "transformers_version": "4.57.1", "use_cache": true, "vocab_size": 262272, "zaya_mlp_expansion": 256, "zaya_use_eda": true, "zaya_use_mod": true }