maldv commited on
Commit
f91e61f
·
verified ·
1 Parent(s): 3845cd5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -13,9 +13,9 @@ license: cc-by-nc-4.0
13
 
14
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/SpNOAI3VKUsWegChuQHTk.png)
15
 
16
- Badger Writer is a *normalized fourier task addition* of maldv/badger-lambda-llama-3-8b and maldv/llama-3-fantasy-writer-8b.
17
 
18
- I also used the first and last layer directly from dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5 due to the obvious advantages. I didn't train either the lm_head or embed_token layers on the fantasy-writer, but opus is part of lambda ; so they all fit nicely together.
19
 
20
  Rep-pen 1.1 ; Min-p 0.01 ; Temp 0.7 ; Dynatemp 0.4 ; 32k context ; llama 3 instruct template
21
 
 
13
 
14
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/SpNOAI3VKUsWegChuQHTk.png)
15
 
16
+ Badger Writer is a *normalized fourier task addition* of [maldv/badger-lambda-llama-3-8b](/maldv/badger-lambda-llama-3-8b) and [maldv/llama-3-fantasy-writer-8b](/maldv/llama-3-fantasy-writer-8b).
17
 
18
+ I also used the first and last layer directly from [dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5](/dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5) due to the obvious advantages. I didn't train either the lm_head or embed_tokens layers on the fantasy-writer, but opus is part of lambda ; so they all fit nicely together.
19
 
20
  Rep-pen 1.1 ; Min-p 0.01 ; Temp 0.7 ; Dynatemp 0.4 ; 32k context ; llama 3 instruct template
21