{ "architectures": [ "BananaMind21UnifiedForCausalLM" ], "model_type": "bananamind21_unified", "auto_map": { "AutoConfig": "configuration_bananamind21unified.BananaMind21UnifiedConfig", "AutoModelForCausalLM": "modeling_bananamind21unified.BananaMind21UnifiedForCausalLM" }, "vocab_size": 8192, "head_dim": 64, "max_position_embeddings": 4096, "rope_theta": 100000.0, "rms_norm_eps": 1e-06, "embed_width": 384, "hidden_size_a": 256, "num_hidden_layers_a": 14, "num_attention_heads_a": 4, "num_key_value_heads_a": 1, "intermediate_size_a": 704, "hidden_size_b": 320, "num_hidden_layers_b": 5, "num_attention_heads_b": 5, "num_key_value_heads_b": 1, "intermediate_size_b": 960, "hidden_size_c": 384, "num_hidden_layers_c": 6, "num_attention_heads_c": 6, "num_key_value_heads_c": 2, "intermediate_size_c": 1024, "a_read": [ 5, 9, 12 ], "a_land": [ 7, 11, 14 ], "c_read": [ 2, 4, 5 ], "c_land": [ 3, 5, 6 ], "b_land": [ 1, 3, 5 ], "b_read": [ 2, 4, 5 ], "gate_init": 0.01, "cut_bridges": false, "hidden_size": 384, "tie_word_embeddings": false, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 0, "torch_dtype": "float32", "_name_or_path": "Banaxi-Tech/unified-2.1-test" }