| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "ffn_activation": "silu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 4, | |
| "position_embedding_type": "rotary", | |
| "sliding_window": 256, | |
| "tie_word_embeddings": true, | |
| "use_rms_norm": true, | |
| "use_swiglu": true, | |
| "vocab_size": 50257 | |
| } |