{ "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_time0": 2, "cca_time1": 2, "clamp_temp": false, "dtype": "bfloat16", "eos_token_id": 106, "ffn_hidden_size": 4096, "gated_linear_unit": true, "head_dim": 128, "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": 8, "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, "residual_in_fp32": true, "rope_parameters": { "partial_rotary_factor": 0.5, "rope_theta": 5000000, "rope_type": "default" }, "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_high_prec": true, "zaya_mlp_expansion": 256, "zaya_use_eda": true, "zaya_use_mod": true, "quantization_config": { "quant_method": "compressed-tensors", "format": "nvfp4-pack-quantized", "config_groups": { "group_0": { "weights": { "num_bits": 4, "type": "float", "strategy": "tensor_group", "group_size": 16, "symmetric": true, "dynamic": false }, "input_activations": { "num_bits": 4, "type": "float", "strategy": "tensor_group", "group_size": 16, "symmetric": true, "dynamic": false }, "targets": [ "Linear" ] } }, "ignore": [ "lm_head", "re:.*router.*", "re:.*norm.*", "re:.*qkv.*", "re:.*cca.*", "re:model\\.layers\\.(1|19|31|37|39|65|69|71|73|75|77|79)\\..+" ] } }