Upload folder using huggingface_hub

README.md

@@ -9,7 +9,7 @@ base_model: google/gemma-3-4b-it
 
 This is my first finetune. I used GRPO to reduce slop output.
 
-This is a LoRA adapter, it needs to be merged with google/gemma-3-4b-it.
+This is a LoRA adapter, it needs to be merged with [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
 
 I'll also upload a Q4_K_M GGUF made with unsloth's imatrix.
 
@@ -21,12 +21,18 @@ I added some of these to the reward function and penalized their use.
 
 I also added some regex filters for comma overuse, and some sloppy phrasing, etc.
 
-Halfway thru traning I activate lexical diversity comparison. It penalizes MTLD < 100, gives increasing rewards up to 120.
+200 steps into training I activate lexical diversity comparison. It penalizes MTLD < 100, gives increasing rewards up to 120.
 
 There's a callback for early stopping if reward stays high, but it didn't kick in this run.
 
+This was trained on ~15 million tokens on a single 3090. I'm sharing my code so people can try their own finetuning runs.
+
 I'll probably keep iterating on this a bit, and may update this model.
 
 training code: [train.py](./train.py)
 
 I can't share my dataset, but here's an example of what it looks like: [dataset_example.json](./dataset_example.json)
+
+Gemma 3 4b common bigrams, most common first: [bigrams.txt](./bigrams.txt)
+
+Gemma 3 4b common trigrams, most common first: [trigrams.txt](./trigrams.txt)