Rename repo to bert-esi-triage-v57; align with v49/v50 convention; update internal references

README.md

@@ -15,7 +15,7 @@ tags:
 - not-for-clinical-use
 base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
 model-index:
-- name: esi-triage-v57
+- name: bert-esi-triage-v57
   results:
   - task:
       type: text-classification
@@ -68,11 +68,11 @@ model-index:
       value: 0.943
 ---
 
-# ESI Triage v57 — BiomedBERT multi-head triage classifier
+# BERT-ESI-Triage v57 — BiomedBERT multi-head triage classifier
 
 ## TL;DR
 
-`esi-triage-v57` is a fine-tuned BiomedBERT classifier for the
+`bert-esi-triage-v57` is a fine-tuned BiomedBERT classifier for the
 **Emergency Severity Index (ESI 1-5)** triage decision. It is the first
 model in this line to meet ESI 1 safety recall **≥75% on every primary
 eval slice** (MIMIC, MC-MED, MIETIC, Lukina), with a mean ESI 1 recall
@@ -125,7 +125,7 @@ class V57BertESI(nn.Module):
 
 tok = AutoTokenizer.from_pretrained(ENCODER)
 model = V57BertESI()
-ckpt = torch.load(hf_hub_download("vadimbelsky/esi-triage-v57", "model.pt"),
+ckpt = torch.load(hf_hub_download("vadimbelsky/bert-esi-triage-v57", "model.pt"),
                   map_location="cpu", weights_only=False)
 # Many auxiliary heads in the checkpoint are not needed for ESI inference.
 sd = model.state_dict()
@@ -317,7 +317,7 @@ prevalence of ESI 1 varies materially across input formats
             engine ensemble safety floor},
   author = {Belski, Vadim},
   year   = {2026},
-  url    = {https://huggingface.co/vadimbelsky/esi-triage-v57},
+  url    = {https://huggingface.co/vadimbelsky/bert-esi-triage-v57},
   note   = {Validated on 18-eval suite: MIMIC-IV-ED holdout, MC-MED
             Stanford clean, MIETIC narrative clean, Lukina v3,
             7 condition-specific slices, 6 subgroup slices. v57 epoch 3.
@@ -335,3 +335,4 @@ prevalence of ESI 1 varies materially across input formats
   retired in favor of v57 for new deployments).
 - **Successor:** v58 (training in progress as of 2026-06-01; targets
   six corpus fixes for tightened ESI 2 / ESI 5 boundaries).
+