| { |
| "attn": null, |
| "attn_mode": "chunk", |
| "bos_token_id": 1, |
| "conv_size": 4, |
| "eos_token_id": 2, |
| "expand_k": 1, |
| "expand_v": 1, |
| "fuse_cross_entropy": true, |
| "fuse_norm": true, |
| "hidden_act": "swish", |
| "hidden_ratio": 4, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": null, |
| "model_type": "delta_net", |
| "norm_eps": 1e-06, |
| "num_heads": 16, |
| "num_hidden_layers": 24, |
| "pad_token_id": 2, |
| "qk_activation": "silu", |
| "qk_norm": "l2", |
| "tie_word_embeddings": false, |
| "use_beta": true, |
| "use_cache": true, |
| "use_gate": false, |
| "use_output_norm": true, |
| "use_short_conv": true |
| } |
