Update README.md

README.md

@@ -8,14 +8,20 @@ tags:
 license: apache-2.0
 language:
 - en
+datasets:
+- chimbiwide/pippa_filtered
 ---
 
-# Uploaded finetuned  model
+# Gemma3NPC-filtered-float16
 
-- **Developed by:** chimbiwide
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
+#### The "filtered" model that delivers censored general role-playing at great speed.
 
-This gemma3n model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+We trained this model as a rank-12 LoRA adapter with one epoch over `pippa_filtered` using a 40GB vRAM A100 in Google Colab. For this run, we employed a learning rate of `2e-5` and a total batch size of 1 and gradient accumulation steps of 16. A cosine learning rate scheduler was used with a 150-step warmup. With a gradient clipping of 0.5.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+Check out our training notebook [here](https://github.com/chimbiwide/Gemma3NPC/blob/main/Training/Gemma3NPC-Filtered.ipynb).
+
+---
+
+Here is a graph of the Step Training Loss, saved every 5 steps:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/lr8ubWOj6HCo_cH_L023o.png)