Update README.md

README.md

@@ -47,7 +47,7 @@ base_model:
 
 This is a pre-alpha proof-of-concept of **a real fully uncensored vision model**.
 
-Why do I say **"real"**? The few vision models we got (qwen, llama 3.2) were "censored," and their fine-tunes were made only for the **text portion** of the model, as training a vision model is a serious pain.
+Why do I say **"real"**? The few vision models we got (qwen, llama 3.2) were "censored," and their fine-tunes were made only to the **text portion** of the model, as training a vision model is a serious pain.
 
 The only actually trained and uncensored vision model I am aware of is [ToriiGate](https://huggingface.co/Minthy/ToriiGate-v0.4-7B); the rest of the vision models are just the stock vision + a fine-tuned LLM.
 
@@ -94,11 +94,13 @@ As you probably figured by the email address name, this is not my main email, an
 ---
 
 ### TL;DR
-- **Fully uncensored and trained** so there's no moderation in the vision model, I actually did train it.
-- **The 2nd uncensored vision model in the world**, ToriiGate being the first as far as I know.
+- **Fully uncensored and trained** there's no moderation in the vision model, I actually trained it.
+- **The 2nd uncensored vision model in the world**, ToriiGate being the first as far as I know, and this one is the second.
 - **In-depth descriptions** very detailed, long descriptions.
 - The text portion is **somewhat uncensored** as well, I didn't want to butcher and fry it too much, so it remain "smart".
 - **NOT perfect** This is a POC that shows that the task can even be done, a lot more work is needed.
+- **Good Roleplay & Writing** I used a massive corpus of high quality human (**~60%**) and synthetic data.
+
 
 ---