Update README.md

README.md

@@ -23,13 +23,13 @@ tags:
 
 # HRM-Text-1B
 
-A 1 B-parameter language model checkpoint built on the **Hierarchical Reasoning Model (HRM)** architecture, trained from scratch on a curated text corpus by Sapient Intelligence.
+A 1 B-parameter language model checkpoint built on the **Hierarchical Reasoning Model (HRM)** architecture, trained by Sapient Intelligence from scratch on structured public datasets. 
 
 HRM is a dual-timescale recurrent architecture: two Transformer modules (H = high-level / slow, L = low-level / fast) iterate over the same input embeddings for `H_cycles × (L_cycles + 1)` steps, with additive state injection (`z_L + z_H`). This gives effectively unbounded compute depth at bounded parameter count.
 
 ## Disclaimer
 
-This is a **pre-alignment** model checkpoint, not a chat or instruction-following assistant. It is pre-trained on a PrefixLM objective with condition prefix tokens and has **not** been multi-turn dialogue tuned, long-context adapted, instruction-tuned, RLHF-trained, or otherwise aligned for assistant-style use. If you want to use HRM-Text like a chat model, you should perform further alignment, such as SFT and/or RL, on task-specific data. This checkpoint is meant as a starting point, not a finished assistant.
+This is a **pre-alignment** model checkpoint, not a chat or instruction-following assistant. It is pre-trained on a PrefixLM objective with condition prefix tokens and has **not** been multi-turn dialogue tuned, long-context adapted, instruction-tuned, RLHF-trained, or otherwise aligned for assistant-style use. If you want to use HRM-Text like a chat model, you would need to perform further alignment, such as SFT and/or RL, on task-specific data. This checkpoint is meant to serve as a starting point, not a finished assistant.
 
 Practical guidance for prompting the raw checkpoint:
 
@@ -138,6 +138,7 @@ Pre-trained on a sampled mixture of publicly available text corpora. The full da
 ## Limitations
 
 - English only (training corpus is predominantly English).
+- HRM-Text-1B was not trained on code datasets, so the raw checkpoint is expected to be weak at coding tasks. Early third-party code SFT experiments on roughly 1B tokens of code data improved coding benchmark scores from low single digits to around 40–50, suggesting promising adaptation potential, but those results are not part of this checkpoint.
 - Outputs may be inaccurate, biased, or unsafe.
 
 ## License