Update README.md

README.md

@@ -7,7 +7,7 @@ tags:
 - merge
 license: llama3
 ---
-# Meta-Llama-3-13B-Instruct
+# Meta-Llama-3-13B-Instruct-ft
 
 This is a QLoRA **finetune** of a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
@@ -15,16 +15,20 @@ The model is based on my passthrough merge of [Llama-3-13B-Instruct](https://hug
 
 This was primarily an experiment to see how a passthrough merge will respond to further finetuning, though this was done on a small dataset.
 
-The model was finetuned on 8192 context length and is likely reliable using RoPE scaling up to 32k.
+The goal was to make a "mid" sized model like Meta has released in the past and the merge method was inspired by [mlabonne's Llama-3-120B](https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct).
 
-It still cannot do math reliably; neither can Llama-3-8B, and in my tests only Llama-3-70B can, but it a better storywriter/RP than Llama-3-8B from some side by side testing.
+The model was finetuned on **8192 context length** and is likely reliable using RoPE up to 32k.
 
-## Dataset
+It still cannot do math reliably; neither can Llama-3-8B, and in my tests only Llama-3-70B passes simple arithmetic, but it a better storywriter/RP than Llama-3-8B from some side by side testing I conducted.
 
-* Dataset used
-   * [Chat-Error/Pure-dove-sharegpt](https://huggingface.co/datasets/Chat-Error/Pure-dove-sharegpt)
+Further finetuning this model or finetuning the [base model](https://huggingface.co/elinas/Llama-3-13B-Instruct) on more samples is encouraged.
+
+## Datasets
+
+* [Chat-Error/Pure-dove-sharegpt](https://huggingface.co/datasets/Chat-Error/Pure-dove-sharegpt)
 
 A small dataset was used to see how it affects performance. Originally I planned to do a larger dataset (196k samples), but wanted to start with a smaller one first to see how much the model improved with some additional finetuning. 
+
 Next steps would be finetuning on a larger dataset if through further testing, performance improvements are noticed.
 
 ## Finetuning details