RichardErkhov/hedronstone_-_OpenHermes-7B-Symbolic-gguf

Quantization made by Richard Erkhov.

OpenHermes-7B-Symbolic - GGUF

Model creator: https://huggingface.co/hedronstone/
Original model: https://huggingface.co/hedronstone/OpenHermes-7B-Symbolic/

Name	Quant method	Size
OpenHermes-7B-Symbolic.Q2_K.gguf	Q2_K	2.53GB
OpenHermes-7B-Symbolic.IQ3_XS.gguf	IQ3_XS	2.81GB
OpenHermes-7B-Symbolic.IQ3_S.gguf	IQ3_S	2.96GB
OpenHermes-7B-Symbolic.Q3_K_S.gguf	Q3_K_S	2.95GB
OpenHermes-7B-Symbolic.IQ3_M.gguf	IQ3_M	3.06GB
OpenHermes-7B-Symbolic.Q3_K.gguf	Q3_K	3.28GB
OpenHermes-7B-Symbolic.Q3_K_M.gguf	Q3_K_M	3.28GB
OpenHermes-7B-Symbolic.Q3_K_L.gguf	Q3_K_L	3.56GB
OpenHermes-7B-Symbolic.IQ4_XS.gguf	IQ4_XS	3.67GB
OpenHermes-7B-Symbolic.Q4_0.gguf	Q4_0	3.83GB
OpenHermes-7B-Symbolic.IQ4_NL.gguf	IQ4_NL	3.87GB
OpenHermes-7B-Symbolic.Q4_K_S.gguf	Q4_K_S	3.86GB
OpenHermes-7B-Symbolic.Q4_K.gguf	Q4_K	4.07GB
OpenHermes-7B-Symbolic.Q4_K_M.gguf	Q4_K_M	4.07GB
OpenHermes-7B-Symbolic.Q4_1.gguf	Q4_1	4.24GB
OpenHermes-7B-Symbolic.Q5_0.gguf	Q5_0	4.65GB
OpenHermes-7B-Symbolic.Q5_K_S.gguf	Q5_K_S	4.65GB
OpenHermes-7B-Symbolic.Q5_K.gguf	Q5_K	4.78GB
OpenHermes-7B-Symbolic.Q5_K_M.gguf	Q5_K_M	4.78GB
OpenHermes-7B-Symbolic.Q5_1.gguf	Q5_1	5.07GB
OpenHermes-7B-Symbolic.Q6_K.gguf	Q6_K	5.53GB
OpenHermes-7B-Symbolic.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0

OpenHermes-7B-Symbolic

Model description

OpenHermes-7B-Symbolic is a OpenHermes-2.5-Mistral-7B fine-tuned on 93K comprehensive and meticulously curated samples. Each sample was structured to facilitate the model's understanding and generation of complex, hierarchical ICD medical coding system.

Benchmark	OpenHermes-7B-Symbolic	OpenHermes-2.5-Mistral-7B
Average	64.44	65.26
ARC	63.14	64.93
HellaSwag	82.73	84.18
MMLU	62.62	63.64
TruthfulQA	48.82	52.24
Winogrande	75.85	78.06
GSM8K	53.45	48.52