Downloads · 30 days
0
mats-gf-metadata-tags-probes
siddharthmb/mats-gf-metadata-tags-probes
mats-gf-metadata-tags-probes is a machine learning model from siddharthmb. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Trained linear probes from the fine-tune-time metadata tags project. Each probe reads mean-pooled residual-stream activations at one layer and detects whether a document's content-token embeddings carried an additive…
Access
Public
Updated Jul 22, 2026
Repo size
2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.6 MB · 77%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- b9e76890
Model card
From the Hugging Face model README
Fine-tune-time metadata tags — code-detector probes
Trained linear probes from the fine-tune-time metadata tags project. Each probe reads mean-pooled residual-stream activations at one layer and detects whether a document's content-token embeddings carried an additive embedding code (injection strength α = 0.3 or 0.1), for both model families. Whitening statistics are stored inside each checkpoint.
Contents
| Subfolder | Source training run | Model | Files |
|---|---|---|---|
exp2-embedding-codes/ | Experiment 2 — embedding codes | Qwen3-8B (layers 0–36, step 4) | probe_alpha{0.3,0.1}fc_L{layer}.pt, metrics_alpha{0.3,0.1}.json (recorded per-layer AUROC; layer-24 α=0.3 dev AUROC 0.901) |
exp8-llama-transfer/ | Experiment 8 — model-family transfer | Llama-3.1-8B (layers 0–27) | probe_alpha{0.3,0.1}fc_L{layer}.pt, per-doc dev_scores_*.npz, metrics_*.json |
Loading
Each .pt is a plain dict: state_dict (linear weight/bias), layer, d_model, and whitening stats norm_mu / norm_sd. Score a mean-pooled residual vector x as:
import torch
from huggingface_hub import hf_hub_download
p = torch.load(
hf_hub_download(
"siddharthmb/mats-gf-metadata-tags-probes",
"exp2-embedding-codes/probe_alpha0.3fc_L24.pt",
),
map_location="cpu", weights_only=False,
)
w, b = p["state_dict"]["classifier.weight"][0], p["state_dict"]["classifier.bias"][0]
score = ((x - p["norm_mu"]) / p["norm_sd"]) @ w + b # > 0 → code present
(The GitHub repo's src/gf_metadata_tags/embedding_codes/ has the exact probe class and evaluation code.)
Links
- Code and reproduction anchors: https://github.com/Sid-MB/mats-gf-metadata-tags
- Paper (PDF in-repo): https://github.com/Sid-MB/mats-gf-metadata-tags/tree/main/paper
- Companion repos: adapters · codebook · data
- License
- mit
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026