Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ tags:
|
|
| 7 |
---
|
| 8 |
# Aegolius Acadicus 30B
|
| 9 |
|
|
|
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
I like to call this model "The little professor". It is simply a MOE merge of lora merged models across Llama2 and Mistral. I am using this as a test case to move to larger models and get my gate discrimination set correctly. This model is best suited for knowledge related use cases, I did not give it a specific workload target as I did with some of the other models in the "Owl Series".
|
|
|
|
| 7 |
---
|
| 8 |
# Aegolius Acadicus 30B
|
| 9 |
|
| 10 |
+
This model placed 16th on the leaderboard when first run, but for some bizarre reason got removed. I really don't appreciate it much since I fund all of my work out of my own pocket and work as hard as anyone else at this. I also share all of my work without restriction. I was honestly stunned that it did so well and then equally as stunned someone took it down. It is just an MOE model just like mixtral. I just happened to land the right gates or something I guess? I am going to resubmit if possible. Again I pay for this on rental gear and runpod.
|
| 11 |
+
|
| 12 |
|
| 13 |
|
| 14 |
I like to call this model "The little professor". It is simply a MOE merge of lora merged models across Llama2 and Mistral. I am using this as a test case to move to larger models and get my gate discrimination set correctly. This model is best suited for knowledge related use cases, I did not give it a specific workload target as I did with some of the other models in the "Owl Series".
|