Update README.md

README.md

@@ -17,10 +17,10 @@ pipeline_tag: feature-extraction
 
 # GeneJEPA — A Perceiver-style JEPA for scRNA-seq
 
-**GeneJEPA** is a Joint-Embedding Predictive Architecture (JEPA) trained for self-supervised representation learning on single-cell RNA-seq.  
-It uses a Perceiver-style encoder to handle sparse, high-dimensional gene count vectors and learns from masked block prediction—no labels required.
+**GeneJEPA** is a Joint-Embedding Predictive Architecture (JEPA) trained for self-supervised representation learning on scRNA-seq.  
+It uses a Perceiver-style encoder to handle sparse, high-dimensional gene count vectors and learns from masked block prediction.
 
-> **Why?** Produce compact cell embeddings you can use for clustering, transfer learning, linear probes, and downstream biological tasks.
+**Why?** Produce compact cell embeddings you can use for clustering, transfer learning, linear probes, and downstream biological tasks.
 
 ---
 
@@ -51,15 +51,13 @@ This model repo intentionally contains **artifacts only** (no training code):
 ```python
 from huggingface_hub import hf_hub_download
 
-ckpt_path = hf_hub_download(repo_id="<your-username>/<your-model-id>",
+ckpt_path = hf_hub_download(repo_id="elonlit/GeneJEPA",
                             filename="genejepa-epoch=49.ckpt")
-meta_path = hf_hub_download(repo_id="<your-username>/<your-model-id>",
+meta_path = hf_hub_download(repo_id="elonlit/GeneJEPA",
                             filename="gene_metadata.parquet")
-stats_path = hf_hub_download(repo_id="<your-username>/<your-model-id>",
+stats_path = hf_hub_download(repo_id="elonlit/GeneJEPA",
                              filename="global_stats.json")
 ```
 ## Contact
 
-elonlit@biostate.ai
-
-
+elonlit@biostate.ai