Update README.md

README.md

@@ -26,13 +26,13 @@ The MediPhi Model Collection comprises 7 small language models of 3.8B parameter
 ## Model Details
 ### Model Description
 
-This model is the `MediPhi-Instruct` aligned to accomplish clinical NLP tasks.
+This model is `MediPhi` obtained by merging all 5 experts with the BreadCrumbs technique into this unified expert.
 
 - **Developed by:** Microsoft Healthcare \& Life Sciences
 - **Model type:** Phi3
 - **Language(s) (NLP):** English
 - **License:** MIT
-- **Finetuned from model:** `microsoft/MediPhi`, and originally from `microsoft/Phi-3.5-mini-instruct`
+- **Finetuned from model:** `microsoft/Phi-3.5-mini-instruct`
 
 ### Model Sources
 
@@ -90,7 +90,7 @@ Researchers should apply responsible AI best practices, including mapping, measu
 
     torch.random.manual_seed(0)
 
-    model_name = "microsoft/MediPhi-Instruct"
+    model_name = "microsoft/MediPhi"
     model = AutoModelForCausalLM.from_pretrained(
         model_name,
         device_map="cuda",
@@ -142,9 +142,6 @@ Continual Pre-training:
     - `zhengyun21/PMC-Patients`, `akemiH/NoteChat`, and `starmpcc/Asclepius-Synthetic-Clinical-Notes` (only commercial-friendly licenses across all three datasets)
     - mtsamples
 
-Clinical alignment:
-- `microsoft/mediflow`
-
 See paper for details.
 
 ### Training Procedure