docs(card): fix Model Description architecture mislabel and parameter count + fix Usage example

README.md

@@ -20,7 +20,7 @@ pipeline_tag: fill-mask
 
 ## Model Description
 
-GPT-2 medium (345M parameters) foundation model pre-trained on RNA gene expression sequences from the MolCrawl dataset.
+BERT-medium foundation model (~332M parameters, 24-layer / 1024-hidden / 16-head topology, sized to match GPT-2-medium) pre-trained on RNA gene expression sequences from the MolCrawl dataset.
 
 - **Model Type**: bert
 - **Data Type**: RNA
@@ -28,31 +28,40 @@ GPT-2 medium (345M parameters) foundation model pre-trained on RNA gene expressi
 
 ## Usage
 
+This tokenizer is a WordLevel vocab of ENSEMBL gene IDs only (no text-mode
+pre-tokenizer). Feed the input as a Python list of gene-ID tokens (one
+position may be `tokenizer.mask_token`) and resolve to IDs through
+`convert_tokens_to_ids` — calling `tokenizer("AUGC...")` on raw nucleotide
+strings collapses to `[UNK]` and the MLM head returns a uniform-prior
+prediction.
+
 ```python
-from transformers import AutoModelForMaskedLM, AutoTokenizer
 import torch
+from transformers import AutoModelForMaskedLM, AutoTokenizer
 
-model = AutoModelForMaskedLM.from_pretrained("kojima-lab/molcrawl-rna-bert-medium")
-tokenizer = AutoTokenizer.from_pretrained("kojima-lab/molcrawl-rna-bert-medium")
+REPO_ID = "kojima-lab/molcrawl-rna-bert-medium"
+tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
+model = AutoModelForMaskedLM.from_pretrained(REPO_ID)
+model.eval()
 
-# Predict masked RNA token
-# Use tokenizer.mask_token instead of hardcoded "[MASK]":
-# BERT-style tokenizers vary ("[MASK]", "<mask>", etc.)
-if tokenizer.mask_token is None:
-    raise ValueError("This tokenizer has no mask_token; masked LM inference is not supported.")
-prompt = "AUGCAUGC{MASK}AUGCAUGC".replace("{MASK}", tokenizer.mask_token)
-inputs = tokenizer(prompt, return_tensors="pt")
-mask_index = (inputs["input_ids"] == tokenizer.mask_token_id).nonzero(as_tuple=True)[1]
+# Gene-expression masked prediction (ENSEMBL gene IDs in rank order).
+genes = [
+    "ENSG00000000003",
+    "ENSG00000000005",
+    tokenizer.mask_token,   # mask one position to predict
+    "ENSG00000001167",
+    "ENSG00000002586",
+]
+ids = tokenizer.convert_tokens_to_ids(genes)
+input_ids = torch.tensor([ids])
+mask_index = (input_ids == tokenizer.mask_token_id).nonzero(as_tuple=True)[1]
 
 with torch.no_grad():
-    outputs = model(**inputs)
-logits = outputs.logits
-
-predicted_token_id = logits[0, mask_index].argmax(dim=-1)
-predicted_token = tokenizer.decode(predicted_token_id)
-result = prompt.replace(tokenizer.mask_token, predicted_token)
-print(f"Predicted: {result}")
+    outputs = model(input_ids=input_ids)
 
+predicted_id = outputs.logits[0, mask_index].argmax(dim=-1)
+predicted_gene = tokenizer.convert_ids_to_tokens(predicted_id.tolist())[0]
+print(f"Predicted gene at mask: {predicted_gene}")
 ```
 
 ## Source Code