{ "architectures": [ "DharaARForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_dhara_ar.DharaARConfig", "AutoModelForCausalLM": "modeling_dhara_ar.DharaARForCausalLM" }, "canon_activation": false, "canon_bias": false, "canon_kernel": 4, "canon_residual": true, "canon_set": "ABCD", "dtype": "bfloat16", "hidden_act": "silu", "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 2176, "logit_softcap": 30.0, "mask_token_id": 49152, "max_position_embeddings": 32768, "mlp_bias": false, "model_type": "dhara_ar", "num_attention_heads": 12, "num_hidden_layers": 32, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_parameters": null, "rope_theta": 8000000.0, "tie_word_embeddings": true, "transformers_version": "5.8.1", "use_logit_softcap": true, "use_qk_norm": true, "vocab_size": 49155 }