Downloads · 30 days
0
agamemnon/talkie-web-13b-base-jspace
talkie-web-13b-base-jspace is a machine learning model from agamemnon. 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 jlens. The card lists the license as apache-2.0.
This repository contains a Jacobian-lens J-space matrix for xlr8harder/talkie-web-13b-base-tf.
Downloads · 30 days
0
Access
Public
Updated Jul 17, 2026
Repo size
2.5 GB
Likes
0
Public
Click a slice to open those files.
.pt2 GB · 100%
From the Hugging Face model README
This repository contains a Jacobian-lens J-space matrix for
xlr8harder/talkie-web-13b-base-tf.
This matrix was freshly fit by the Talkie J-Space project. It was computed from the pinned
Talkie checkpoint and shared prompt corpus recorded in manifest.json. It was not copied,
converted, averaged, or downloaded from any pre-existing Talkie J-space or Jacobian-lens artifact.
The repository intentionally contains no Talkie model weights and no fitting checkpoint.
| Field | Value |
|---|---|
| Model | xlr8harder/talkie-web-13b-base-tf |
| Model revision | 963f2bba0c3fceacb69f57f671015ca3eb162808 |
| Source layers | 0–38 |
| Target layer | 39 |
| Residual width | 5120 |
| Prompts completed | 100 |
| Maximum prompt length | 128 tokens |
| Dimension batch | 56 |
| GPU | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Corpus | Salesforce/wikitext |
| Corpus revision | b08601e04326c79dfdd32d625aee71d232d685c3 |
| Jacobian Lens revision | 581d398613e5602a5af361e1c34d3a92ea82ba8e |
| Artifact SHA-256 | 67aa49577fc30f2ef9935158b8c1021339dd806f51c70b149ed7ba8ec1f6744b |
| Artifact bytes | 2044734799 |
The artifact has 39 fp16 matrices of shape 5120 × 5120, mapping residual states from
layers 0–38 into the layer-39 basis. manifest.json is the
machine-readable source of truth for exact provenance and checksum verification.
from jlens import JacobianLens
lens = JacobianLens.from_pretrained("agamemnon/talkie-web-13b-base-jspace")
print(lens.source_layers, lens.d_model)
Use the exact model revision in manifest.json with the Talkie adapter from the Talkie J-Space
backend. A Jacobian lens is architecture- and revision-specific.
This is an interpretability research artifact, not a factuality or safety classifier. J-space readouts can be misleading and should be validated against model behavior. Raw base-model output can be inaccurate, biased, or unsuitable for all audiences.
The matrix and project-authored metadata are released under Apache-2.0. Upstream Apache-2.0, MIT,
CC-BY-SA, and GFDL attributions are in THIRD_PARTY_NOTICES.md. The underlying model remains
subject to its own model card and license.