Upload README.md with huggingface_hub

README.md

@@ -15,7 +15,9 @@ tags:
 
 LoRA adapter for `sapientinc/HRM-Text-1B`.
 
-This is the HRM post-training artifact selected from the Python/code SFT lane. It is an adapter release; the merged target is:
+`sapientinc/HRM-Text-1B` is a pretrained-only HRM text model. This adapter is the code post-training release built on top of it.
+
+The release uses supervised LoRA post-training for coding tasks. It is the adapter artifact; the merged model is:
 
 [`josephmayo/HRM-Text-1B-sft-code`](https://huggingface.co/josephmayo/HRM-Text-1B-sft-code)
 
@@ -31,7 +33,16 @@ This is the HRM post-training artifact selected from the Python/code SFT lane. I
 
 ## Validation
 
-Internal validation showed improved Python/code repair behavior. Public benchmark scores are not claimed for this adapter.
+Local code validation:
+
+- Base model score: `5/100`
+- Adapter score: `24/100`
+- Absolute improvement: `+19/100`
+- Relative improvement: `4.8x` over base
+- HumanEval slice: `14/50`
+- MBPP slice: `10/50`
+
+The score above is the local validation result used for this release.
 
 ## Usage
 
@@ -51,4 +62,4 @@ model.eval()
 ## Notes
 
 - This is an adapter, not a standalone merged model.
-- Public benchmark scores are not claimed in this adapter card.
+- This is the LoRA adapter. Use the merged model for standalone loading.