Upload folder using huggingface_hub

README.md

@@ -1,25 +1,29 @@
-# TabPFN Transcriptome 32D Model
+---
+tags:
+- transcriptomics
+- dimensionality-reduction
+- tabpfn
+- TRACERx
+license: mit
+---
 
-Pre-computed TabPFN embeddings for transcriptomic data.
+# TabPFN Model - transcriptome mode - 32D
 
-## Contents
-- `model.joblib`: Model bundle with reference embeddings
+Pre-trained TabPFN embedding model with UMAP reduction.
+
+## Details
+- **Mode**: transcriptome-centric compression
+- **Dimensions**: 32
+- **Training data**: TRACERx lung cancer transcriptomics
+- **Created**: 2026-01-13T12:22:39.634119
+- **Reduction method**: UMAP (non-linear)
 
 ## Usage
+
 ```python
 import joblib
-from huggingface_hub import hf_hub_download
+from huggingface_hub import snapshot_download
 
-# Download model
-model_path = hf_hub_download(repo_id="jruffle/tabpfn_transcriptome_32d", filename="model.joblib")
-model = joblib.load(model_path)
-
-# Access embeddings
-embeddings = model['reference_embeddings']
+local_dir = snapshot_download("jruffle/tabpfn_transcriptome_32d")
+model = joblib.load(f"{local_dir}/model.joblib")
 ```
-
-## Details
-- Mode: transcriptome
-- Dimensions: 32
-- Samples: 2405
-- Complete coverage: All samples have TabPFN embeddings

metadata.json

@@ -2,7 +2,7 @@
   "model_type": "tabpfn",
   "mode": "transcriptome",
   "dimensions": 32,
-  "created": "2026-01-10T10:17:30.386254",
+  "created": "2026-01-13T12:22:39.634325",
   "keys": [
     "tabpfn_embedding",
     "input_scaler",

model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfbd98b958b8f05a180af43e708b0df8bfd49e84a87e086b2c322ac13af3ed2
-size 665798
+oid sha256:9bafeea1d3367c0ef4aeee2532112996d686c6a80d3fbb847e249b3d9b9e43a2
+size 131996098