Sao10K/Stheno-Inverted-L2-13B

The sister Model of Stheno-L2-13B

Stheno Inverted:
Gradient Merge of Stheno-P2 & Stheno-P1, Models are in Inverted Positions

Quants courtesy of TheBloke!
GPTQ
GGUF
GGML

Test Checklist:
Censorship - Fairly Uncensored
Writing - Good Prose, Fairly Descriptive
NSFW - Yes
IQ Level - Pretty Smart
Formatting - Proper Formatting with Examples

Noticeable difference with Stheno-L2. From personal tests: A bit more verbose, a little less smart, and a little more forward with NSFW compared to regular Stheno.

Stheno-P1 [Ties-Merge]
-----elinas/chronos-13b-v2
-----jondurbin/airoboros-l2-13b-2.1
-----NousResearch/Nous-Hermes-Llama2-13b+nRuaif/Kimiko-v2 LORA

Stheno-P2 [Ties-Merge]
-----CalderaAI/13B-Legerdemain-L2+lemonilia/limarp-llama2-v2 LORA
-----ehartford/WizardLM-1.0-Uncensored-Llama2-13b
-----Henk717/spring-dragon

Most formats could work, but my tests have all been done in 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:

Below is the Illustration for the Final Merge:

Once Again, thanks to Chargoddard for his amazing and simple ties-merge script, and Gryphe for their great BlockMerge_Gradient script. Thank you to the original model creators too!

Art by wada_kazu / わだかず (pixiv page private?)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	49.57
ARC (25-shot)	59.3
HellaSwag (10-shot)	82.9
MMLU (5-shot)	56.45
TruthfulQA (0-shot)	52.04
Winogrande (5-shot)	74.74
GSM8K (5-shot)	13.19
DROP (3-shot)	8.33