| { | |
| "allow_neg_eigval": false, | |
| "architectures": [ | |
| "GDN2ForCausalLM" | |
| ], | |
| "attn": null, | |
| "attn_mode": "chunk", | |
| "attnres_block_size": null, | |
| "bos_token_id": 1, | |
| "conv_size": 4, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "expand_v": 2, | |
| "fuse_cross_entropy": true, | |
| "fuse_linear_cross_entropy": false, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "head_dim": 64, | |
| "head_init_design": null, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 512, | |
| "initialization_manifest": { | |
| "A_log_rule": "GDN v3_random_a source A_log", | |
| "dt_bias_rule": "GDN-aligned head means with deterministic small channel noise; channel_std=0.03", | |
| "experiment": "v5_random_a", | |
| "family": "GDN2", | |
| "gdn_source_csv": "/root/checkpoints/gdn/training/gdn100m-v3-random-5b-v3_random_a/initial_head_params.csv" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "max_position_embeddings": 4096, | |
| "model_type": "gdn2", | |
| "norm_eps": 1e-06, | |
| "num_heads": 6, | |
| "num_hidden_layers": 18, | |
| "num_v_heads": 6, | |
| "pad_token_id": 0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.9.0", | |
| "use_cache": true, | |
| "use_gate": true, | |
| "use_l2warp": false, | |
| "use_short_conv": true, | |
| "vocab_size": 32000 | |
| } | |