{ "variant": "Weevil-3M", "source_checkpoint": "reports/latent-gdn2-sub3m-tst-8gpu-10b-20261023/step-00038147", "source_model_sha256": "17715c39cc5fb56fd37bd655e98082991440cdc7d462160bfc2678bd0cd8263b", "source_step": 38147, "parameters": 2993576, "model_spec": { "name": "weevil_latent_gdn2_sub3m_v1", "model_class": "WeevilSimpleParallel", "layers_per_stack": 8, "constructor": { "vocab_size": 4096, "embedding_dim": 128, "intermediate_size": 432 }, "gdn2_config": { "hidden_size": 144, "num_heads": 3, "key_head_dim": 48, "value_head_dim": 48, "qkv_rank": 48, "conv_kernel": 4, "norm_eps": 1e-06, "compute_dtype": "bfloat16", "mixer": "chunk", "chunk_size": null, "prefix_block_size": null }, "parameter_budget": { "exclusive_upper_limit": 3000000, "expected_total": 2993576, "embedding": 542720, "mlp": 1492992, "mixers": 956568, "normalization": 1296, "qkv_subset_of_mixers": 221184 } }, "weights_dtype": "float32" }