Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ Experimental: Created using an unofficial and unsupported method. I have no metr
|
|
| 5 |
|
| 6 |
https://huggingface.co/nkpz/llama2-22b-blocktriangular-alpaca with further conversational and instruction fine tuning
|
| 7 |
|
| 8 |
-
First, I trained it on an epoch of https://huggingface.co/datasets/Adapting/empathetic_dialogues_v2 to give it a decent base knowledge of a casual chat style. The result was conversational, but not very smart.
|
| 9 |
|
| 10 |
Then I trained it on an epoch of https://huggingface.co/datasets/vicgalle/alpaca-gpt4 and landed here, a model that is capable of chatting but very focused on following instructions.
|
| 11 |
|
|
|
|
| 5 |
|
| 6 |
https://huggingface.co/nkpz/llama2-22b-blocktriangular-alpaca with further conversational and instruction fine tuning
|
| 7 |
|
| 8 |
+
First, I trained it on an epoch of https://huggingface.co/datasets/Adapting/empathetic_dialogues_v2 to give it a decent base knowledge of a casual chat style. I added some automated capitalization fixes for this data.The result was conversational, but not very smart.
|
| 9 |
|
| 10 |
Then I trained it on an epoch of https://huggingface.co/datasets/vicgalle/alpaca-gpt4 and landed here, a model that is capable of chatting but very focused on following instructions.
|
| 11 |
|