Sao10K_-_Stheno-Mix-L2-20B-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
Sao10K_-_Stheno-Mix-L2-20B-gguf

like

0

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Stheno-Mix-L2-20B - GGUF

Model creator: https://huggingface.co/Sao10K/
Original model: https://huggingface.co/Sao10K/Stheno-Mix-L2-20B/

Name	Quant method	Size
Stheno-Mix-L2-20B.Q2_K.gguf	Q2_K	7.13GB
Stheno-Mix-L2-20B.IQ3_XS.gguf	IQ3_XS	3.23GB
Stheno-Mix-L2-20B.IQ3_S.gguf	IQ3_S	0.93GB
Stheno-Mix-L2-20B.Q3_K_S.gguf	Q3_K_S	8.32GB
Stheno-Mix-L2-20B.IQ3_M.gguf	IQ3_M	2.41GB
Stheno-Mix-L2-20B.Q3_K.gguf	Q3_K	1.74GB
Stheno-Mix-L2-20B.Q3_K_M.gguf	Q3_K_M	3.42GB
Stheno-Mix-L2-20B.Q3_K_L.gguf	Q3_K_L	1.19GB
Stheno-Mix-L2-20B.IQ4_XS.gguf	IQ4_XS	0.41GB
Stheno-Mix-L2-20B.Q4_0.gguf	Q4_0	2.27GB
Stheno-Mix-L2-20B.IQ4_NL.gguf	IQ4_NL	10.91GB
Stheno-Mix-L2-20B.Q4_K_S.gguf	Q4_K_S	9.38GB
Stheno-Mix-L2-20B.Q4_K.gguf	Q4_K	11.59GB
Stheno-Mix-L2-20B.Q4_K_M.gguf	Q4_K_M	5.62GB
Stheno-Mix-L2-20B.Q4_1.gguf	Q4_1	4.48GB
Stheno-Mix-L2-20B.Q5_0.gguf	Q5_0	3.62GB
Stheno-Mix-L2-20B.Q5_K_S.gguf	Q5_K_S	2.27GB
Stheno-Mix-L2-20B.Q5_K.gguf	Q5_K	0.68GB
Stheno-Mix-L2-20B.Q5_K_M.gguf	Q5_K_M	0.32GB
Stheno-Mix-L2-20B.Q5_1.gguf	Q5_1	0.27GB
Stheno-Mix-L2-20B.Q6_K.gguf	Q6_K	0.19GB
Stheno-Mix-L2-20B.Q8_0.gguf	Q8_0	0.11GB

Original model description:

license: llama2 language:

en

See https://huggingface.co/The-Face-Of-Goonery/Huginn-19b-prototype ?

Stheno-20B is even more stupid, uses the same technique as above, just slightly different params.

a 64-layer splice of Stheno P1 and P2.

Hey, it works... decently well.

Meme model that somehow isn't as bad as I thought.

Ty Chargoddard for mergekit.

Stheno v2 on the way soon, Euryale-70B progress stalled for now, Medusa-7B soonTM

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.76
ARC (25-shot)	57.76
HellaSwag (10-shot)	79.63
MMLU (5-shot)	52.51
TruthfulQA (0-shot)	51.8
Winogrande (5-shot)	68.98
GSM8K (5-shot)	0.08
DROP (3-shot)	9.53