Stheno
Collection
Variants of the Stheno series of Models I've done [L2-13B]
•
14 items
•
Updated
•
2
ONLY UPLOADED FROM RUNPOD JUST TO TEST ON OWN SYSTEM. UNTESTED SO FAR. V2 SOON
CURRENT CHANGES: INCREASED BASE MODEL WEIGHTS AND DENSITIES BEFORE MERGE + DIFFERENT GRADIENTS APPLIED
An experimental merging of Several Models using two various methods, Ties-Merge and BlockMerge_Gradient
Stheno:
Gradient Merge of Stheno-P1 & Stheno-P2.
Test Checklist:
Censorship - ____
Writing - ____
NSFW - ___
IQ Level - ___
Formatting - ____
Most formats could work, use Alpaca format and it works well.
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
Gradient Merge Pictures Unavailable, Several Different Tensor Ratios applied.
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 54.43 |
ARC (25-shot) | 60.75 |
HellaSwag (10-shot) | 83.64 |
MMLU (5-shot) | 56.39 |
TruthfulQA (0-shot) | 50.3 |
Winogrande (5-shot) | 75.22 |
GSM8K (5-shot) | 7.96 |
DROP (3-shot) | 46.78 |