Update README.md

README.md

@@ -16,9 +16,9 @@ pipeline_tag: text-generation
 library_name: transformers
 ---
 
-# Quark-72M-Instruct
+# Quark-72M
 
-**Quark-72M-Instruct** is a compact, from-scratch autoregressive language model developed by [ThingAI](https://things-ai.org) as part of the **Quark** family of small language models. It is designed to be lightweight enough to run on consumer hardware while remaining architecturally modern, using Grouped-Query Attention, RoPE positional embeddings, SwiGLU feed-forward layers, and RMSNorm — the same building blocks found in contemporary frontier models, scaled down to ~72M parameters.
+**Quark-72M** is a compact, from-scratch autoregressive language model developed by [ThingAI](https://things-ai.org) as part of the **Quark** family of small language models. It is designed to be lightweight enough to run on consumer hardware while remaining architecturally modern, using Grouped-Query Attention, RoPE positional embeddings, SwiGLU feed-forward layers, and RMSNorm — the same building blocks found in contemporary frontier models, scaled down to ~72M parameters.
 
 This is an **instruction-tuned** checkpoint, fine-tuned via SFT on top of a base model pre-trained on math, code, and reasoning-focused corpora.
 
@@ -289,10 +289,10 @@ If you use Quark-72M-Instruct in your work, please consider citing the repositor
 
 ```bibtex
 @misc{quark72m,
-  title  = {Quark-72M-Instruct},
+  title  = {Quark-72M},
   author = {ThingAI},
   year   = {2026},
-  url    = {https://huggingface.co/ThingAI/Quark-72M-Instruct}
+  url    = {https://huggingface.co/ThingAI/Quark-72M}
 }
 ```
 
@@ -304,4 +304,4 @@ This model is released under the **MIT License**. See the repository for full li
 
 ---
 
-*Quark-72M-Instruct is developed and maintained by [ThingAI](https://things-ai.org) as part of an ongoing effort to build self-hostable, fully-inspectable small language models.*
+*Quark-72M is developed and maintained by [ThingAI](https://things-ai.org) as part of an ongoing effort to build self-hostable, fully-inspectable small language models.*