Delta-Vector commited on
Commit
eb668cc
·
verified ·
1 Parent(s): 182f727

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -23
README.md CHANGED
@@ -8,29 +8,12 @@ tags:
8
  - merge
9
 
10
  ---
11
- # gemma-ln
12
 
13
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
 
14
 
15
- ## Merge Details
16
- ### Merge Method
17
 
18
- This model was merged using the Passthrough merge method using [unsloth/gemma-3-12b-it](https://huggingface.co/unsloth/gemma-3-12b-it) + [NewEden/Gemma-LN-Lora](https://huggingface.co/NewEden/Gemma-LN-Lora) as a base.
19
-
20
- ### Models Merged
21
-
22
- The following models were included in the merge:
23
-
24
-
25
- ### Configuration
26
-
27
- The following YAML configuration was used to produce this model:
28
-
29
- ```yaml
30
- base_model: unsloth/gemma-3-12b-it+NewEden/Gemma-LN-Lora
31
- dtype: bfloat16
32
- merge_method: passthrough
33
- models:
34
- - model: unsloth/gemma-3-12b-it+NewEden/Gemma-LN-Lora
35
-
36
- ```
 
8
  - merge
9
 
10
  ---
11
+ Hparams:
12
 
13
+ - LR: 1e-5
14
+ - Weight Decay: 0.02
15
+ - grad-clip: 0.2
16
 
17
+ pretrained on a buncha LNs, books, etc.
18
+ Used for a base for Pascal.
19