| { | |
| "architectures": [ | |
| "CatsModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "cats.CatsConfig", | |
| "AutoModelForCausalLM": "cats.CatsModel" | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "cats_model", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "target_modules": [ | |
| "act_fn" | |
| ], | |
| "target_sparsity": 0.5, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "wrapped_model_class_name": "MistralForCausalLM" | |
| } | |