| { |
| "architectures": [ |
| "ModularStarEncoder" |
| ], |
| "attention_dropout": 0.1, |
| "auto_map": { |
| "AutoConfig": "config.ModularStarEncoderConfig", |
| "AutoModel": "modularStarEncoder.ModularStarEncoder" |
| }, |
| "bos_token_id": 0, |
| "conditional_size": 4, |
| "embedding_dropout": 0.1, |
| "eos_token_id": 0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1024, |
| "initializer_range": 0.018042, |
| "intermediate_size": 12288, |
| "keys_to_ignore_at_inference": "past_key_values", |
| "layer_matryoshka_loss": true, |
| "layer_norm_eps": 1e-05, |
| "matryoshka_layers": [ |
| 4, |
| 9, |
| 18, |
| 27, |
| 36 |
| ], |
| "max_position_embeddings": 2048, |
| "mlp_type": "default", |
| "model_type": "ModularStarEncoder", |
| "norm_epsilon": 1e-05, |
| "norm_type": "layer_norm", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 4, |
| "residual_dropout": 0.1, |
| "rope_theta": 999999.4420358813, |
| "sliding_window": null, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.39.3", |
| "use_bias": true, |
| "use_cache": false, |
| "vocab_size": 49156 |
| } |
|
|
