{ "architectures": [ "NandiForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_nandi.NandiConfig", "AutoModel": "modeling_nandi.NandiModel", "AutoModelForCausalLM": "modeling_nandi.NandiForCausalLM" }, "bos_token_id": 1, "dtype": "bfloat16", "embedding_rank": 196, "eos_token_id": 0, "factorized_embedding": true, "head_dim": 52, "hidden_act": "silu", "hidden_size": 832, "initializer_range": 0.02, "intermediate_size": 2496, "layer_sharing": true, "layer_sharing_repeats": 2, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "nandi", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 4, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 100000, "rope_type": "default" }, "tie_word_embeddings": true, "transformers_version": "5.4.0", "use_cache": false, "vocab_size": 131072 }