Fixed-State GDN Paper 120M, Q/K Head Dim 128, V Head Dim 64
This repository contains the final PyTorch Lightning checkpoint for the
fixed-state Gated DeltaNet language-model experiment
m06d10y26-gdn-paper-qk128-v64-fp32res-gpt2init-20k-r1.
The model has 12 layers, hidden size 768, and 12 heads. Each head uses a fixed Q/K feature dimension of 128 and a V dimension of 64. This is an ordinary fixed-state GDN: it does not use a growing-state mask or an expansion schedule.
Files
last.ckpt: final checkpoint, byte-identical to the Perlmutterstep_20000.ckpt.train_config.yaml: exact training config preserved in the archived GDN branch.eval_metrics.json: training/evaluation provenance, metrics, and the checkpoint SHA-256 digest.
Provenance
- Training run:
m06d10y26-gdn-paper-qk128-v64-fp32res-gpt2init-20k-r1. - Training Slurm job:
54260616. - Training source commit recorded by W&B:
9b40978e08d174bb24b1c675cdc1d2a655996ab4. - Preserved config/code branch:
HazyResearch/mlp-mixercommitd2b24d685bc12f6e974d3ce68ffe2563a477cea1. - W&B: hazy-research/mlp-mixer.
Architecture
- Hidden size:
768 - Layers:
12 - Heads:
12 - Q/K head dimension:
128 - V head dimension:
64(expand_v=0.5) - Independent Q/K projections:
1 - Residual stream: FP32
- Residual-output initialization: GPT-2 normal
- Recurrent state: fixed-size
Metrics
- Full Pile validation PPL from the finished W&B run:
10.2112963416. - Full Pile validation loss:
2.3234939575over7,667,089,408tokens. - Independent Pile validation 10% PPL at sequence length 2048:
10.1007396226. - Rare-AR overall PPL at sequence length 2048:
10.1014004483. - Rare-AR selected accuracy:
0.708458599321over1,156,539selected event tokens.
Usage Note
This is a Lightning checkpoint for the custom mlp-mixer / Gated DeltaNet
training and evaluation stack, not a standalone Transformers-format model.
Use a compatible checkout of the preserved GDN branch and load last.ckpt
through that stack. The repository's existing checkpoint downloader convention
expects this filename.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support