| { | |
| "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": 64, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 64, | |
| "max_position_embeddings": 2048, | |
| "model_type": "sparse_llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "thresholds": [ | |
| 0.12938815355300903, | |
| 0.12938815355300903, | |
| 0.1313941776752472, | |
| 0.12337010353803635 | |
| ], | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.2", | |
| "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 | |
| } | |