Update README.md
Browse files
README.md
CHANGED
|
@@ -2,10 +2,8 @@
|
|
| 2 |
license: cc-by-nd-4.0
|
| 3 |
base_model: []
|
| 4 |
tags:
|
| 5 |
-
-
|
| 6 |
-
- merge
|
| 7 |
---
|
| 8 |
# This is an experimental model that I made by merging two Llama2 70b models and gluing them together with the mergekit of llama70b. The mergekit is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.
|
| 9 |
|
| 10 |
-
The merged model has 55 billion parameters and was made trained on 640GB of vram cluster
|
| 11 |
-
|
|
|
|
| 2 |
license: cc-by-nd-4.0
|
| 3 |
base_model: []
|
| 4 |
tags:
|
| 5 |
+
- dpo
|
|
|
|
| 6 |
---
|
| 7 |
# This is an experimental model that I made by merging two Llama2 70b models and gluing them together with the mergekit of llama70b. The mergekit is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.
|
| 8 |
|
| 9 |
+
The merged model has 55 billion parameters and was made trained on 640GB of vram cluster
|
|
|