| { | |
| "architectures": [ | |
| "TFMTableForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "silu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "tfm", | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |