Kooten commited on
Commit
c823117
1 Parent(s): b796739

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -14
README.md CHANGED
@@ -3,9 +3,21 @@ language:
3
  - en
4
  pipeline_tag: text-generation
5
  ---
 
6
  # DaringMaid-20B
7
- My initial goal was to make a Noromaid that's smarter and better at following instructions.
 
 
 
 
 
 
 
 
8
 
 
 
 
9
 
10
  # Quants
11
  [GGUF](https://huggingface.co/Kooten/DaringMaid-20B-GGUF), EXL2: [6bpw](https://huggingface.co/Kooten/DaringMaid-20B-6bpw-exl2), [3bpw](https://huggingface.co/Kooten/DaringMaid-20B-3bpw-exl2)
@@ -23,16 +35,3 @@ Below is an instruction that describes a task. Write a response that appropriate
23
  ### Response:
24
 
25
  ```
26
- # Parts
27
-
28
- - I used [DynamicFactor](https://huggingface.co/sequelbox/DynamicFactor) as a base to "improve overall knowledge, precise communication, conceptual understanding, and technical skill" over the base llama2
29
- - [Noromaid](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1) of course
30
- - [Utopia](https://huggingface.co/Undi95/Utopia-13B) has been recommended again recently and its still really good so in the mixer it goes
31
- - I enjoyed [Rose](https://huggingface.co/tavtav/Rose-20B) so i threw in a bit of [Thorns](https://huggingface.co/CalderaAI/13B-Thorns-l2)
32
- - There was recently a model that tried to pass itself off as [MythoMax](https://huggingface.co/Gryphe/MythoMax-L2-13b), i made a merge with it before i knew it was just MythoMax but i actually really liked the result, i think it improved the ability to follow instructions a lot.
33
-
34
-
35
-
36
-
37
-
38
-
 
3
  - en
4
  pipeline_tag: text-generation
5
  ---
6
+
7
  # DaringMaid-20B
8
+ My Initial goal was to make a Noromaid that's smarter and better at following instructions.
9
+
10
+ After trying a bunch of different recipes I think this one turned out pretty good
11
+
12
+ - I used [sequelbox/DynamicFactor](https://huggingface.co/sequelbox/DynamicFactor) as a base to as its supposed "improve overall knowledge, precise communication, conceptual understanding, and technical skill" over the base llama2.
13
+ - [NeverSleep/Noromaid](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1) of course.
14
+ - [Undi95/Utopia](https://huggingface.co/Undi95/Utopia-13B) has been recommended again recently and its still really good so in the mixer it goes
15
+ - I enjoyed [tavtav/Rose](https://huggingface.co/tavtav/Rose-20B) so i threw in a bit of [CalderaAI/Thorns](https://huggingface.co/CalderaAI/13B-Thorns-l2)
16
+ - There was recently a model that tried to pass itself off as [Gryphe/MythoMax](https://huggingface.co/Gryphe/MythoMax-L2-13b), i made a merge with that model before it was revealed to be MythoMax and it turned out pretty good.
17
 
18
+ The .yml config files with the exact merges can be found in the "Recipe" folder in the [fp16 repo](https://huggingface.co/Kooten/DaringMaid)
19
+
20
+ There is no wisdom to be found there, i do not know what i am doing.
21
 
22
  # Quants
23
  [GGUF](https://huggingface.co/Kooten/DaringMaid-20B-GGUF), EXL2: [6bpw](https://huggingface.co/Kooten/DaringMaid-20B-6bpw-exl2), [3bpw](https://huggingface.co/Kooten/DaringMaid-20B-3bpw-exl2)
 
35
  ### Response:
36
 
37
  ```