Update README.md
Browse files
README.md
CHANGED
@@ -24,7 +24,6 @@ This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com
|
|
24 |
* [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
|
25 |
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
|
26 |
|
27 |
-
|
28 |
It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
|
29 |
|
30 |
Here, we are controlling layers checking which ones have lower signal to noise ratios (which are more subject to noise), to apply Laser interventions, still using Machenko Pastur to calculate this ratio.
|
@@ -32,3 +31,9 @@ Here, we are controlling layers checking which ones have lower signal to noise r
|
|
32 |
We intend to be the first of a family of experimentations being carried out @ Cognitive Computations.
|
33 |
|
34 |
In this experiment we have observed very high truthfulness and high reasoning capabilities.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
* [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
|
25 |
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
|
26 |
|
|
|
27 |
It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
|
28 |
|
29 |
Here, we are controlling layers checking which ones have lower signal to noise ratios (which are more subject to noise), to apply Laser interventions, still using Machenko Pastur to calculate this ratio.
|
|
|
31 |
We intend to be the first of a family of experimentations being carried out @ Cognitive Computations.
|
32 |
|
33 |
In this experiment we have observed very high truthfulness and high reasoning capabilities.
|
34 |
+
|
35 |
+
# Evals
|
36 |
+
|
37 |
+
|
38 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/j_fg_zwGXC1RS9npuJMAK.png)
|
39 |
+
|