chargoddard_-_MelangeA-70b-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
chargoddard_-_MelangeA-70b-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

MelangeA-70b - GGUF

Model creator: https://huggingface.co/chargoddard/
Original model: https://huggingface.co/chargoddard/MelangeA-70b/

Name	Quant method	Size
MelangeA-70b.Q2_K.gguf	Q2_K	23.71GB
MelangeA-70b.IQ3_XS.gguf	IQ3_XS	26.37GB
MelangeA-70b.IQ3_S.gguf	IQ3_S	27.86GB
MelangeA-70b.Q3_K_S.gguf	Q3_K_S	27.86GB
MelangeA-70b.IQ3_M.gguf	IQ3_M	28.82GB
MelangeA-70b.Q3_K.gguf	Q3_K	30.99GB
MelangeA-70b.Q3_K_M.gguf	Q3_K_M	30.99GB
MelangeA-70b.Q3_K_L.gguf	Q3_K_L	33.67GB
MelangeA-70b.IQ4_XS.gguf	IQ4_XS	34.64GB
MelangeA-70b.Q4_0.gguf	Q4_0	36.2GB
MelangeA-70b.IQ4_NL.gguf	IQ4_NL	36.55GB
MelangeA-70b.Q4_K_S.gguf	Q4_K_S	36.55GB
MelangeA-70b.Q4_K.gguf	Q4_K	38.58GB
MelangeA-70b.Q4_K_M.gguf	Q4_K_M	38.58GB
MelangeA-70b.Q4_1.gguf	Q4_1	40.2GB
MelangeA-70b.Q5_0.gguf	Q5_0	44.2GB
MelangeA-70b.Q5_K_S.gguf	Q5_K_S	44.2GB
MelangeA-70b.Q5_K.gguf	Q5_K	45.41GB
MelangeA-70b.Q5_K_M.gguf	Q5_K_M	45.41GB
MelangeA-70b.Q5_1.gguf	Q5_1	48.2GB
MelangeA-70b.Q6_K.gguf	Q6_K	52.7GB
MelangeA-70b.Q8_0.gguf	Q8_0	68.26GB

Original model description: Experimental merge. Details to come if successful.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	55.92
ARC (25-shot)	71.25
HellaSwag (10-shot)	87.3
MMLU (5-shot)	70.56
TruthfulQA (0-shot)	60.61
Winogrande (5-shot)	81.53
GSM8K (5-shot)	5.69
DROP (3-shot)	14.53