athirdpath commited on
Commit
011d917
1 Parent(s): 4f4a764

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -24
README.md CHANGED
@@ -1,42 +1,59 @@
1
  ---
2
  license: cc-by-nc-4.0
3
  ---
4
- merge_method: dare_ties
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
- base_model: athirdpath/BigLlama-20B
7
 
8
- models:
9
 
10
- - model: athirdpath/BigLlama-20B
 
 
 
 
 
11
 
12
  - model: NeverSleep/Noromaid-20b-v0.1.1
13
- -
14
- parameters:
15
-
16
- weight: 0.41
17
-
18
- density: 0.50
19
 
20
  - model: athirdpath/Eileithyia-20b
21
- -
22
- parameters:
23
-
24
- weight: 0.18
25
-
26
- density: 0.30
27
 
28
  - model: athirdpath/CleverGirl-20b-Blended
29
- -
30
- parameters:
31
-
32
- weight: 0.41
33
-
34
- density: 0.50
35
 
36
 
37
  int8_mask: true
38
 
39
  dtype: bfloat16
40
 
41
-
42
- Thanks to brucethemoose for the recipe.
 
1
  ---
2
  license: cc-by-nc-4.0
3
  ---
4
+ <p align="center"><img src="https://i.ibb.co/pbpJHpk/iambe-sml.png"/><font size="6"> <b>Iambe-L2-32b</b> </font></p>
5
+
6
+ ## Description and Role
7
+
8
+ Named after a charming daughter of Echo and Pan in Greek myth, Iambe-20b-DARE is a [DARE](https://github.com/yule-BUAA/MergeLM) merge building on my recent experiments.
9
+ Iambe is intended to be a model that has the best realisticly possible understanding of the scene state
10
+ remains personable and "human-like" in RP scenarios,
11
+
12
+ ## Prompting and Context
13
+
14
+ Iambe-20b-DARE uses Alpaca formatting, and has an effective context size of 4096 tokens. This model is uncensored, and the output/deployment of this model is the responsibility of the user.
15
+
16
+ ## Method and Hypothesis
17
+
18
+ Based on my extended vanilla model [BigLlama](https://github.com/yule-BUAA/MergeLM), this adds elements of:
19
+
20
+ - NeverSleep/Noromaid-20b-v0.1.1 - Addded to adapt the excellent writing and "soul" that come from the datasets backing this model.
21
+
22
+ - athirdpath/Eileithyia-20b - Added at low weight and density to capture anatomical data and its relation to fiction without the model's other... quirks.
23
+
24
+ - athirdpath/CleverGirl-20b-Blended - Added to capture CleverGirl's problem-solving abilities.
25
+
26
+ ## Examples
27
+
28
+ Coming soon.
29
 
30
+ ## Testing and Conclusions
31
 
32
+ VERY Impressed so far, concrete data coming soonish.
33
 
34
+ Does still have some confusion (at q5_k_m), but has instantly become my daily driver.
35
+
36
+ ## Recipe
37
+ merge_method: dare_ties
38
+
39
+ - base_model: athirdpath/BigLlama-20B
40
 
41
  - model: NeverSleep/Noromaid-20b-v0.1.1
42
+
43
+ weight: 0.41 / density: 0.50
 
 
 
 
44
 
45
  - model: athirdpath/Eileithyia-20b
46
+
47
+ weight: 0.18 / density: 0.30
 
 
 
 
48
 
49
  - model: athirdpath/CleverGirl-20b-Blended
50
+
51
+ weight: 0.41 / density: 0.50
 
 
 
 
52
 
53
 
54
  int8_mask: true
55
 
56
  dtype: bfloat16
57
 
58
+ ## Gratitude
59
+ Thanks to brucethemoose for the recipe. Thanks to Undi95 and IkariDev at NeverSleep for Noromaid, as well as lots of inspiration. Thanks to Sao10K for half of CleverGirl.