{ "architectures": [ "Evo2ForCausalLM" ], "attn_block_dtype": "bfloat16", "attn_layer_idxs": [ 3, 10, 17, 24, 31 ], "auto_map": { "AutoConfig": "configuration_evo2.Evo2Config", "AutoModel": "modeling_evo2.Evo2Model", "AutoModelForCausalLM": "modeling_evo2.Evo2ForCausalLM" }, "column_split": true, "column_split_hyena": false, "dtype": "bfloat16", "eps": 1e-06, "evo2_style_activations": true, "final_norm": true, "hcl_filter_groups": 4096, "hcl_layer_idxs": [ 2, 6, 9, 13, 16, 20, 23, 27, 30 ], "hcm_filter_groups": 256, "hcm_filter_length": 128, "hcm_layer_idxs": [ 1, 5, 8, 12, 15, 19, 22, 26, 29 ], "hcs_filter_groups": 256, "hcs_filter_length": 7, "hcs_layer_idxs": [ 0, 4, 7, 11, 14, 18, 21, 25, 28 ], "hidden_size": 4096, "hyena_block_dtype": "bfloat16", "hyena_filter_groups": 1, "hyena_flip_x1x2": false, "hyena_out_proj_bias": true, "inference_mode": true, "inner_mlp_size": 11008, "inner_size_multiple_of": 16, "interleave": true, "log_intermediate_values": false, "make_vocab_size_divisible_by": 8, "max_batch_size": 1, "max_seqlen": 262144, "mha_out_proj_bias": true, "mlp_activation": "gelu", "mlp_dtype": "bfloat16", "mlp_init_method": "torch.nn.init.zeros_", "mlp_output_init_method": "torch.nn.init.zeros_", "model_parallel_size": 1, "model_type": "evo2", "num_attention_heads": 32, "num_filters": 4096, "num_layers": 32, "pipe_parallel_size": 1, "prefill_style": "fft", "print_activations": false, "proj_groups": 1, "qkv_proj_bias": false, "rotary_emb_base": 10000, "rotary_emb_scaling_factor": 32, "short_filter_bias": false, "short_filter_length": 3, "smeared_gqa": false, "state_size": 16, "tie_embeddings": true, "transformers_version": "4.57.6", "use_cache": true, "use_flash_attn": false, "use_flash_depthwise": false, "use_flash_rmsnorm": false, "use_flashfft": false, "use_fp8_input_projections": false, "use_interpolated_rotary_pos_emb": true, "use_laughing_hyena": false, "vocab_size": 512, "model_max_length": 262144 }