Add some clarification on what exactly this model is
Browse files
README.md
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
Continuation of https://huggingface.co/nkpz/llama2-22b-daydreamer-v2
|
| 5 |
|
| 6 |
Gave it an epoch of https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1-mpt which it had never seen before - it had only seen Airoboros 2.0.
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
| 4 |
+
**What is it?**
|
| 5 |
+
Llama 2 13b expanded to the size of a Llama 1 33b model, with the empty surrounding space filled with llama 33b data. (Base Model: https://huggingface.co/chargoddard/llama2-22b-blocktriangular) This is then finetuned on a 3090 by creating large loras and merging them.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
|
| 9 |
Continuation of https://huggingface.co/nkpz/llama2-22b-daydreamer-v2
|
| 10 |
|
| 11 |
Gave it an epoch of https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1-mpt which it had never seen before - it had only seen Airoboros 2.0.
|