Undi95/ReMM-L2-13B-PIPPA

Re:MythoMax-PIPPA (ReMM-PIPPA) is a recreation trial of the original MythoMax-L2-B13 with updated models and merge of the PIPPA dataset (PIPPA-ShareGPT-Subset-QLora-13b) at (0.18) weight.

Command useds and explaination :

Due to hardware limitation, some merge was done in 2 part.

- Recreate ReML : Mythologic (v2) (Chronos/Hermes/Airboros)
=> Replacing Chronos by The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 (0.30)
=> Replacing Airoboros by jondurbin/airoboros-l2-13b-2.1 (last version) (0.40)
=> Keeping NousResearch/Nous-Hermes-Llama2-13b (0.30)

Part 1: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B-part1  --merge The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 --density 0.42 --merge jondurbin/airoboros-l2-13b-2.1 --density 0.56 --cuda

Part 2: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B --merge NousResearch/Nous-Hermes-Llama2-13b --density 0.30 --merge Undi95/ReML-L2-13B-part1 --density 0.70 --cuda

With that :
- Recreate ReMM : MythoMax (v2) (Mythologic/Huginn v1)
=> Replacing Mythologic by the one above (0.5)
=> Replacing Huginn by The-Face-Of-Goonery/Huginn-13b-v1.2 (hottest) (0.5)

Part 3: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReMM-L2-13B  --merge Undi95/ReML-L2-13B --density 0.50 --merge The-Face-Of-Goonery/Huginn-13b-v1.2  --density 0.50 --cuda
Part 4: Undi95/ReMM-L2-13B (0.82) + zarakiquemparte/PIPPA-ShareGPT-Subset-QLora-13b (0.18) = ReMM-L2-13B-PIPPA

Description

This repo contains fp16 files of ReMM-PIPPA, a recreation of the original MythoMax, but updated and merged with the PIPPA dataset.

Models used

• TheBloke/Llama-2-13B-fp16 (base)
• The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
• jondurbin/airoboros-l2-13b-2.1
• NousResearch/Nous-Hermes-Llama2-13b
• The-Face-Of-Goonery/Huginn-13b-v1.2
• ReML-L2-13B (Private recreation trial of an updated Mythologic-L2-13B)

Loras used

• zarakiquemparte/PIPPA-ShareGPT-Subset-QLora-13b

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Special thanks to Sushi kek

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.58
ARC (25-shot)	59.73
HellaSwag (10-shot)	83.12
MMLU (5-shot)	54.1
TruthfulQA (0-shot)	49.94
Winogrande (5-shot)	74.51
GSM8K (5-shot)	2.96
DROP (3-shot)	43.69