You can deploy this model and start earning money today!

RichardErkhov/
Undi95_-_ReMM-L2-13B-v1-gguf

Name: Undi95_-_ReMM-L2-13B-v1-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ReMM-L2-13B-v1 - GGUF

Model creator: https://huggingface.co/Undi95/
Original model: https://huggingface.co/Undi95/ReMM-L2-13B-v1/

Name	Quant method	Size
ReMM-L2-13B-v1.Q2_K.gguf	Q2_K	4.52GB
ReMM-L2-13B-v1.IQ3_XS.gguf	IQ3_XS	4.99GB
ReMM-L2-13B-v1.IQ3_S.gguf	IQ3_S	5.27GB
ReMM-L2-13B-v1.Q3_K_S.gguf	Q3_K_S	5.27GB
ReMM-L2-13B-v1.IQ3_M.gguf	IQ3_M	5.57GB
ReMM-L2-13B-v1.Q3_K.gguf	Q3_K	5.9GB
ReMM-L2-13B-v1.Q3_K_M.gguf	Q3_K_M	5.9GB
ReMM-L2-13B-v1.Q3_K_L.gguf	Q3_K_L	6.45GB
ReMM-L2-13B-v1.IQ4_XS.gguf	IQ4_XS	6.54GB
ReMM-L2-13B-v1.Q4_0.gguf	Q4_0	6.86GB
ReMM-L2-13B-v1.IQ4_NL.gguf	IQ4_NL	6.9GB
ReMM-L2-13B-v1.Q4_K_S.gguf	Q4_K_S	6.91GB
ReMM-L2-13B-v1.Q4_K.gguf	Q4_K	7.33GB
ReMM-L2-13B-v1.Q4_K_M.gguf	Q4_K_M	7.33GB
ReMM-L2-13B-v1.Q4_1.gguf	Q4_1	7.61GB
ReMM-L2-13B-v1.Q5_0.gguf	Q5_0	8.36GB
ReMM-L2-13B-v1.Q5_K_S.gguf	Q5_K_S	8.36GB
ReMM-L2-13B-v1.Q5_K.gguf	Q5_K	8.6GB
ReMM-L2-13B-v1.Q5_K_M.gguf	Q5_K_M	8.6GB
ReMM-L2-13B-v1.Q5_1.gguf	Q5_1	9.1GB
ReMM-L2-13B-v1.Q6_K.gguf	Q6_K	9.95GB
ReMM-L2-13B-v1.Q8_0.gguf	Q8_0	12.88GB

Original model description:

license: cc-by-nc-4.0

Re:MythoMax (ReMM) is a recreation trial of the original MythoMax-L2-B13 with updated models.

Command useds and explaination :

shell

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

Description

This repo contains fp16 files of ReMM, a recreation of the original MythoMax, but updated.

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)

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)	83.1
MMLU (5-shot)	54.11
TruthfulQA (0-shot)	49.94
Winogrande (5-shot)	74.51
GSM8K (5-shot)	2.96
DROP (3-shot)	43.7

RichardErkhov/Undi95_-_ReMM-L2-13B-v1-gguf