cstr commited on
Commit
09ac4a1
1 Parent(s): 3e7c276

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -14,10 +14,30 @@ This is a progressive (mostly dare-ties, but also slerp) merge with the intentio
14
 
15
  It achives in german EQ Bench: Score (v2_de): 62.59 (Parseable: 171.0).
16
 
 
 
17
  Spaetzle-v69-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
18
  * [abideen/AlphaMonarch-dora](https://huggingface.co/abideen/AlphaMonarch-dora)
19
  * [cstr/Spaetzle-v68-7b](https://huggingface.co/cstr/Spaetzle-v68-7b)
20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  ## 🧩 Configuration
22
 
23
  ```yaml
 
14
 
15
  It achives in german EQ Bench: Score (v2_de): 62.59 (Parseable: 171.0).
16
 
17
+ It should work sufficiently well with ChatML (all merged models should have seen ChatML at least in DPO stage).
18
+
19
  Spaetzle-v69-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
20
  * [abideen/AlphaMonarch-dora](https://huggingface.co/abideen/AlphaMonarch-dora)
21
  * [cstr/Spaetzle-v68-7b](https://huggingface.co/cstr/Spaetzle-v68-7b)
22
 
23
+ The merge tree in total involves to following original models:
24
+ - [abideen/AlphaMonarch-dora]
25
+ - [mayflowergmbh/Wiedervereinigung-7b-dpo]
26
+ - [flemmingmiguel/NeuDist-Ro-7B]
27
+ - [ResplendentAI/Flora_DPO_7B]
28
+ - [yleo/EmertonMonarch-7B]
29
+ - [occiglot/occiglot-7b-de-en-instruct]
30
+ - [OpenPipe/mistral-ft-optimized-1227]
31
+ - [yleo/EmertonMonarch-7B]
32
+ - [DiscoResearch/DiscoLM_German_7b_v1]
33
+ - [LeoLM/leo-mistral-hessianai-7b]
34
+ - [DRXD1000/Phoenix]
35
+ - [VAGOsolutions/SauerkrautLM-7b-v1-mistral]
36
+ - [malteos/hermeo-7b]
37
+ - [FelixChao/WestSeverus-7B-DPO-v2]
38
+ - [cognitivecomputations/openchat-3.5-0106-laser]
39
+
40
+
41
  ## 🧩 Configuration
42
 
43
  ```yaml