Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ tags:
|
|
12 |
- merge
|
13 |
license: llama3.3
|
14 |
---
|
15 |
-
So I was really happy with V3.3 but I got some more advice on the tokenizers as it tended to run a little hot... this is an experiment, in thought I might be able to get better creativity with higher temps. Early testing is not very promising in terms of fixing it from running hot though.
|
16 |
# merge
|
17 |
|
18 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
12 |
- merge
|
13 |
license: llama3.3
|
14 |
---
|
15 |
+
So I was really happy with V3.3 but I got some more advice on the tokenizers as it tended to run a little hot... this is an experiment, in thought I might be able to get better creativity with higher temps. Early testing is not very promising in terms of fixing it from running hot though. But in terms of an expanded vocab it seems a success!
|
16 |
# merge
|
17 |
|
18 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|