| { | |
| "architectures": [ | |
| "BitSkipV3ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "model_v3.BitSkipV3Config", | |
| "AutoModelForCausalLM": "model_v3.BitSkipV3ForCausalLM" | |
| }, | |
| "early_exit_loss_weight": 0.3, | |
| "hidden_size": 2048, | |
| "inference_exit_layer": null, | |
| "intermediate_size": 4096, | |
| "max_dropout_prob": 0.5, | |
| "max_position_embeddings": 2048, | |
| "model_type": "bitskip_v3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.2", | |
| "vocab_size": 50257 | |
| } | |