{ "architectures": [ "DynamicSlidingWindowForCausalLM" ], "attention_bias": false, "auto_map": { "AutoConfig": "configuration_dynamic_sliding_window.DynamicSlidingWindowConfig", "AutoModelForCausalLM": "modeling_dynamic_sliding_window.DynamicSlidingWindowForCausalLM" }, "bos_token_id": null, "context_length": 512, "elementwise_affine": true, "eos_token_id": null, "fuse_cross_entropy": true, "fuse_norm": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": 1024, "max_position_embeddings": null, "model_type": "dynamic_sliding_window", "norm_eps": 1e-06, "num_heads": 4, "num_hidden_layers": 2, "num_kv_heads": null, "qk_norm": false, "qk_norm_share_param_across_head": false, "torch_dtype": "float32", "transformers_version": "4.44.0", "use_cache": true, "use_dynamic_window": true, "use_k_shift": false, "use_rope": false, "use_v_shift": false, "vocab_size": 50277, "window_decay_rate": 0.6, "window_initial_lambda": 1.0, "window_num_epochs": 10 }