Upload folder using huggingface_hub

README.md

@@ -7,15 +7,16 @@ tags:
 license: mit
 ---
 
-# TABPFN Model - samples mode - 4D
+# TabPFN Model - samples mode - 4D
 
-Pre-trained tabpfn model for transcriptomic data compression.
+Pre-trained TabPFN embedding model with UMAP reduction.
 
 ## Details
 - **Mode**: samples-centric compression
 - **Dimensions**: 4
 - **Training data**: TRACERx lung cancer transcriptomics
-- **Created**: 2026-01-10T09:54:04.504720
+- **Created**: 2026-01-13T12:18:18.709280
+- **Reduction method**: UMAP (non-linear)
 
 ## Usage
 
@@ -23,14 +24,6 @@ Pre-trained tabpfn model for transcriptomic data compression.
 import joblib
 from huggingface_hub import snapshot_download
 
-# Download model
 local_dir = snapshot_download("jruffle/tabpfn_samples_4d")
 model = joblib.load(f"{local_dir}/model.joblib")
-
-# For classical models (PCA/UMAP):
-# model contains: 'pca', 'umap', 'robust_scaler', 'gene_order'
-
-# For TabPFN models (with UMAP reduction):
-# model contains: 'tabpfn_embedding', 'umap_final', 'raw_embeddings', 'input_scaler', etc.
-# Uses UMAP instead of PCA for non-linear dimension reduction of TabPFN embeddings
 ```

metadata.json

@@ -2,7 +2,7 @@
   "model_type": "tabpfn",
   "mode": "samples",
   "dimensions": 4,
-  "created": "2026-01-10T09:54:04.504936",
+  "created": "2026-01-13T12:18:18.709465",
   "keys": [
     "tabpfn_embedding",
     "input_scaler",

model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebf81af5ba175bbb0429283b46ee2f1c24d3f73edca3c23032c0b11c67d6f80
-size 63958674
+oid sha256:b6a1ee9a81e5b906feec160071242275d2f1cb1d30ec4ad58e42f98354d6237e
+size 55336114