| { |
| "model_type": "encoder_decoder", |
| "encoder": { |
| "head_dim": 128, |
| "n_embd": 1024, |
| "n_head": 16, |
| "n_hidden": 4096, |
| "n_layer": 12 |
| }, |
| "decoder": { |
| "cross_head_dim": 128, |
| "cross_query_heads": 16, |
| "gqa_head_dim": 128, |
| "gqa_query_heads": 16, |
| "kv_heads": 4, |
| "n_embd": 2048, |
| "n_hidden": 8192, |
| "n_layer": 18 |
| }, |
| "is_encoder_decoder": true, |
| "tie_encoder_decoder": false, |
| "dropout": 0.0, |
| "normalization_layer_epsilon": 1e-05, |
| "rope_max_timescale": 10000, |
| "rope_min_timescale": 1, |
| "src_vocab_size": 256, |
| "tgt_vocab_size": 1028, |
| "weight_dtype": "float32" |
| } |
|
|
