{ "architectures": [ "SDARForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 166100, "eos_token_id": 166101, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 10752, "max_position_embeddings": 262144, "max_window_layers": 22, "model_type": "sdar", "num_attention_heads": 48, "num_hidden_layers": 22, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 70000000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "use_cache": false, "use_sliding_window": false, "vocab_size": 166144, "auto_map": { "AutoConfig": "configuration_sdar.SDARConfig", "AutoModel": "modeling_sdar.SDARModel", "AutoModelForCausalLM": "modeling_sdar.SDARForCausalLM" }, "attn_implementation": "flex_attention", "block_size": 8, "mask_token_id": 166107, "fuse_cross_entropy": true, "pad_token_id": 0, "num_loops": 2, "use_qk_norm": false, "noise": "uniform" }