{ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf", "architectures": [ "SparseLlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "ugly_utils.SparseLlamaConfig", "AutoModelForCausalLM": "ugly_utils.SparseLlamaForCausalLM" }, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "sparse_llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "thresholds": [ 0.051153454929590225, 0.09127381443977356, 0.12136408686637878, 0.14543630182743073, 0.17552657425403595, 0.19759276509284973, 0.22166499495506287, 0.23169508576393127, 0.23771312832832336, 0.24373118579387665, 0.24774321913719177, 0.24974924325942993, 0.2517552673816681, 0.255767285823822, 0.2577733099460602, 0.2617853581905365, 0.2678034007549286, 0.2678034007549286, 0.2718154489994049, 0.27382147312164307, 0.27582746744155884, 0.27582746744155884, 0.27582746744155884, 0.277833491563797, 0.277833491563797, 0.28585755825042725, 0.2938816547393799, 0.3039117157459259, 0.33199599385261536, 0.350050151348114, 0.40020060539245605, 0.5346038341522217 ], "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.2", "us_sparse_regularization": false, "use_cache": true, "use_graceful_regularization": false, "use_relu": false, "use_sparse_model": true, "use_sparse_predictor": false, "use_sparse_regularization": false, "vocab_size": 32000 }