Downloads · 30 days
0
EmmaLeonhart/reservoir-agent-gpt2-batch
reservoir-agent-gpt2-batch is a machine learning model from EmmaLeonhart. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for reservoir-agent. The card lists the license as mit.
A batch of 4 reservoir agents (different fixed-random reservoir seeds) trained on the cross-pass recall task. A reservoir agent is a new model type: a pretrained transformer with a fixed reservoir brain-surgeried in (…
Downloads · 30 days
0
Access
Public
Updated May 31, 2026
Repo size
55.2 MB
Likes
0
Public
Click a slice to open those files.
.npz50.4 MB · 91%
From the Hugging Face model README
A batch of 4 reservoir agents (different fixed-random reservoir seeds)
trained on the cross-pass recall task. A reservoir agent is a new model type: a pretrained
transformer with a fixed reservoir brain-surgeried in (attended, cross-pass-stateful,
RNN-like) — see the project and
RESERVOIR_AGENTS.md.
The whole population is published, not just the winner. Reservoir performance is
stochastic in the seed; the suboptimal models are kept as signal for learning which
reservoir properties survive selection. The recommended model is seed_1.
| rank | seed | recall | loss_end | pr_frac | recommended |
|---|---|---|---|---|---|
| 0 | seed_1 | 1.00 | 0.000 | 0.114 | yes |
| 1 | seed_0 | 1.00 | 0.001 | 0.114 | |
| 2 | seed_2 | 1.00 | 0.001 | 0.113 | |
| 3 | seed_3 | 1.00 | 0.200 | 0.112 |
Each seed_<n>/ is a complete loadable reservoir agent. Load the recommended one:
from huggingface_hub import snapshot_download
from reservoir.persist import load_reservoir_model
path = snapshot_download("EmmaLeonhart/reservoir-agent-gpt2-batch")
lm = load_reservoir_model(f"{path}/seed_1")
batch_manifest.json records the ranking + each seed's score and reservoir-dynamics signal.