{ "architectures": [ "ComplexityForCausalLM" ], "model_type": "complexity", "vocab_size": 100000, "hidden_size": 768, "intermediate_size": 2048, "num_hidden_layers": 12, "num_attention_heads": 12, "num_key_value_heads": 4, "max_position_embeddings": 2048, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "tie_word_embeddings": true, "torch_dtype": "float16", "transformers_version": "4.36.0", "use_token_routed_mlp": true, "num_experts": 4, "use_qk_norm": true, "use_sdpa": true, "sliding_window": null }