| { | |
| "allow_neg_eigval": false, | |
| "architectures": [ | |
| "GatedDeltaNetForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn": null, | |
| "attn_mode": "chunk", | |
| "bos_token_id": 0, | |
| "conv_size": 4, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "expand_v": 2.0, | |
| "fuse_cross_entropy": true, | |
| "fuse_linear_cross_entropy": false, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_ratio": 4, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gated_deltanet", | |
| "norm_eps": 1e-06, | |
| "num_attention_heads": 32, | |
| "num_heads": 6, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "num_v_heads": null, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 130000, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "use_gate": true, | |
| "use_l2warp": false, | |
| "use_short_conv": true, | |
| "vocab_size": 49152 | |
| } | |