Update README.md

README.md

@@ -51,7 +51,7 @@ This is an **instruction-tuned** checkpoint, fine-tuned via SFT on top of a base
 | **Languages** | English, Italian |
 | **License** | MIT |
 | **Finetuned from** | Quark-72M base (pre-trained on math/code/reasoning mix) |
-| **Repository** | [ThingAI/Quark-72M-Instruct](https://huggingface.co/ThingAI/Quark-72M-Instruct) |
+| **Repository** | [ThingAI/Quark-72M](https://huggingface.co/ThingAI/Quark-72M) |
 
 Quark-72M-Instruct is part of a broader effort at ThingAI to build small, self-hostable language models that can be trained, fine-tuned, and served entirely on personal infrastructure — without dependency on third-party APIs. It trades raw capability for transparency, inspectability, and low resource requirements.
 
@@ -59,7 +59,7 @@ Quark-72M-Instruct is part of a broader effort at ThingAI to build small, self-h
 
 ## Architecture
 
-Quark-72M-Instruct uses a standard decoder-only Transformer stack with several efficiency-oriented design choices common in modern small LLMs:
+Quark-72M uses a standard decoder-only Transformer stack with several efficiency-oriented design choices common in modern small LLMs:
 
 | Component | Detail |
 |---|---|
@@ -86,7 +86,7 @@ Quark-72M-Instruct uses a standard decoder-only Transformer stack with several e
 
 ## Intended Use
 
-Quark-72M-Instruct is intended primarily as:
+Quark-72M is intended primarily as:
 
 - A **research and educational artifact** for studying small-scale LLM architecture, training, and inference.
 - A **lightweight conversational base** for hobbyist or self-hosted projects where running a multi-billion-parameter model is impractical.
@@ -162,7 +162,7 @@ At ~72M parameters, this model runs comfortably on CPU for single-turn interacti
 
 ## Prompt Format
 
-Quark-72M-Instruct was fine-tuned using a ChatML-style template with `<|im_start|>` / `<|im_end|>` role delimiters:
+Quark-72M was fine-tuned using a ChatML-style template with `<|im_start|>` / `<|im_end|>` role delimiters:
 
 ```
 <|im_start|>user
@@ -285,7 +285,7 @@ Because this model relies on custom modeling code rather than a built-in `transf
 
 ## Citation
 
-If you use Quark-72M-Instruct in your work, please consider citing the repository:
+If you use Quark-72M in your work, please consider citing the repository:
 
 ```bibtex
 @misc{quark72m,