You can deploy this model and start earning money today!

RichardErkhov/
kheopss_-_kheops-hermes-e1-v0.7-bnb-16bit-gguf

Name: kheopss_-_kheops-hermes-e1-v0.7-bnb-16bit-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

kheops-hermes-e1-v0.7-bnb-16bit - GGUF

Name	Quant method	Size
kheops-hermes-e1-v0.7-bnb-16bit.Q2_K.gguf	Q2_K	2.53GB
kheops-hermes-e1-v0.7-bnb-16bit.IQ3_XS.gguf	IQ3_XS	2.81GB
kheops-hermes-e1-v0.7-bnb-16bit.IQ3_S.gguf	IQ3_S	2.96GB
kheops-hermes-e1-v0.7-bnb-16bit.Q3_K_S.gguf	Q3_K_S	2.95GB
kheops-hermes-e1-v0.7-bnb-16bit.IQ3_M.gguf	IQ3_M	3.06GB
kheops-hermes-e1-v0.7-bnb-16bit.Q3_K.gguf	Q3_K	3.28GB
kheops-hermes-e1-v0.7-bnb-16bit.Q3_K_M.gguf	Q3_K_M	3.28GB
kheops-hermes-e1-v0.7-bnb-16bit.Q3_K_L.gguf	Q3_K_L	3.56GB
kheops-hermes-e1-v0.7-bnb-16bit.IQ4_XS.gguf	IQ4_XS	2.18GB
kheops-hermes-e1-v0.7-bnb-16bit.Q4_0.gguf	Q4_0	3.83GB
kheops-hermes-e1-v0.7-bnb-16bit.IQ4_NL.gguf	IQ4_NL	3.87GB
kheops-hermes-e1-v0.7-bnb-16bit.Q4_K_S.gguf	Q4_K_S	3.86GB
kheops-hermes-e1-v0.7-bnb-16bit.Q4_K.gguf	Q4_K	4.07GB
kheops-hermes-e1-v0.7-bnb-16bit.Q4_K_M.gguf	Q4_K_M	4.07GB
kheops-hermes-e1-v0.7-bnb-16bit.Q4_1.gguf	Q4_1	4.24GB
kheops-hermes-e1-v0.7-bnb-16bit.Q5_0.gguf	Q5_0	0.93GB
kheops-hermes-e1-v0.7-bnb-16bit.Q5_K_S.gguf	Q5_K_S	0.3GB
kheops-hermes-e1-v0.7-bnb-16bit.Q5_K.gguf	Q5_K	0.6GB
kheops-hermes-e1-v0.7-bnb-16bit.Q5_K_M.gguf	Q5_K_M	4.78GB
kheops-hermes-e1-v0.7-bnb-16bit.Q5_1.gguf	Q5_1	4.85GB
kheops-hermes-e1-v0.7-bnb-16bit.Q6_K.gguf	Q6_K	5.53GB
kheops-hermes-e1-v0.7-bnb-16bit.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model: kheopss/kheops-hermes-e1-v0.6-bnb-4bit language:

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.