fernandofernandes commited on
Commit
ae81550
1 Parent(s): c2eff57

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -10
README.md CHANGED
@@ -13,7 +13,7 @@ An experimentation regarding 'lasering' each expert to denoise and enhance model
13
  This model has half size in comparison to the Mixtral 8x7b Instruct. And it basically has the same level of performance (we are working to get a better MMLU score).
14
 
15
 
16
- # Laserxtral - 4x7b (all lasered using laserRMT)
17
 
18
  This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
19
  * [cognitivecomputations/dolphin-2.6-mistral-7b-dpo](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo)
@@ -22,15 +22,6 @@ This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com
22
  * [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
23
  * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
24
 
25
- *mlabonne/Marcoro14-7B-slerp (base)
26
-
27
- *cognitivecomputations/dolphin-2.6-mistral-7b-dpo
28
-
29
- *beowolx/CodeNinja-1.0-OpenChat-7B
30
-
31
- *Q-bert/MetaMath-Cybertron-Starling
32
-
33
- *WizardLM/WizardMath-7B-V1.1
34
 
35
  It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
36
 
 
13
  This model has half size in comparison to the Mixtral 8x7b Instruct. And it basically has the same level of performance (we are working to get a better MMLU score).
14
 
15
 
16
+ # Laserxtral - 4x7b (all, except for base, lasered using laserRMT)
17
 
18
  This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
19
  * [cognitivecomputations/dolphin-2.6-mistral-7b-dpo](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo)
 
22
  * [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
23
  * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
24
 
 
 
 
 
 
 
 
 
 
25
 
26
  It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
27