lnccbrown / lnccbrown/HSSM

LANs for full DDM

Open
#353 1 comment 0 reactions 1 assignee View on GitHub

@AlexanderFengler is already working on this.

Since Feb 16, 2024.

enhancement
Dominant language
Python
Stars
124
Forks
24
Avg merge
19h 32m
Merged PRs (30d)
60

Description

It seems like there is currently no LAN for the full DDM on hugging face. When trying to run this model, I get the error below. It might be just the wrong URL call, but I also don't see any onx file on hugging face that looks like the full DDM (https://huggingface.co/franklab/HSSM/tree/main). Training this LAN would be great so that we can use gradients and don't have to rely on the slice sampler using blackbox likelihood.

FYI, I had to add loglik and backend to the model, I was getting errors pointing in that direction otherwise.

# Load a package-supplied dataset
cav_data = hssm.load_data("cavanagh_theta")

model_safe = hssm.HSSM(
    data=cav_data,
    hierarchical=True,
    prior_settings="safe",
    model="full_ddm",
    loglik_kind="approx_differentiable",
    loglik = "approx_differentiable",
    model_config = {"backend":"jax"}
)
model_safe.sample()

HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/franklab/HSSM/resolve/main/approx_differentiable

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.