You can deploy this model and start earning money today!

RichardErkhov/
augmxnt_-_shisa-gamma-7b-v1-gguf

Name: augmxnt_-_shisa-gamma-7b-v1-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

shisa-gamma-7b-v1 - GGUF

Model creator: https://huggingface.co/augmxnt/
Original model: https://huggingface.co/augmxnt/shisa-gamma-7b-v1/

Name	Quant method	Size
shisa-gamma-7b-v1.Q2_K.gguf	Q2_K	2.53GB
shisa-gamma-7b-v1.Q3_K_S.gguf	Q3_K_S	2.95GB
shisa-gamma-7b-v1.Q3_K.gguf	Q3_K	3.28GB
shisa-gamma-7b-v1.Q3_K_M.gguf	Q3_K_M	3.28GB
shisa-gamma-7b-v1.Q3_K_L.gguf	Q3_K_L	3.56GB
shisa-gamma-7b-v1.IQ4_XS.gguf	IQ4_XS	3.67GB
shisa-gamma-7b-v1.Q4_0.gguf	Q4_0	3.83GB
shisa-gamma-7b-v1.IQ4_NL.gguf	IQ4_NL	3.87GB
shisa-gamma-7b-v1.Q4_K_S.gguf	Q4_K_S	3.86GB
shisa-gamma-7b-v1.Q4_K.gguf	Q4_K	4.07GB
shisa-gamma-7b-v1.Q4_K_M.gguf	Q4_K_M	4.07GB
shisa-gamma-7b-v1.Q4_1.gguf	Q4_1	4.24GB
shisa-gamma-7b-v1.Q5_0.gguf	Q5_0	4.65GB
shisa-gamma-7b-v1.Q5_K_S.gguf	Q5_K_S	4.65GB
shisa-gamma-7b-v1.Q5_K.gguf	Q5_K	4.78GB
shisa-gamma-7b-v1.Q5_K_M.gguf	Q5_K_M	4.78GB
shisa-gamma-7b-v1.Q5_1.gguf	Q5_1	5.07GB
shisa-gamma-7b-v1.Q6_K.gguf	Q6_K	5.53GB
shisa-gamma-7b-v1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 datasets:

augmxnt/ultra-orca-boros-en-ja-v1 language:
ja
en

shisa-gamma-7b-v1

For more information see our main Shisa 7B model

We applied a version of our fine-tune data set onto Japanese Stable LM Base Gamma 7B and it performed pretty well, just sharing since it might be of interest.

Check out our JA MT-Bench results.

Comparison vs other recently released JA models

RichardErkhov/augmxnt_-_shisa-gamma-7b-v1-gguf

Original model description:

shisa-gamma-7b-v1

RichardErkhov/
augmxnt_-_shisa-gamma-7b-v1-gguf