You can deploy this model and start earning money today!

RichardErkhov/
Hello-Bible_-_Gabriel-8x7B-Instruct-v0.1-gguf

Name: Hello-Bible_-_Gabriel-8x7B-Instruct-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Gabriel-8x7B-Instruct-v0.1 - GGUF

Name	Quant method	Size
Gabriel-8x7B-Instruct-v0.1.Q2_K.gguf	Q2_K	16.12GB
Gabriel-8x7B-Instruct-v0.1.IQ3_XS.gguf	IQ3_XS	18.02GB
Gabriel-8x7B-Instruct-v0.1.IQ3_S.gguf	IQ3_S	19.03GB
Gabriel-8x7B-Instruct-v0.1.Q3_K_S.gguf	Q3_K_S	19.03GB
Gabriel-8x7B-Instruct-v0.1.IQ3_M.gguf	IQ3_M	19.96GB
Gabriel-8x7B-Instruct-v0.1.Q3_K.gguf	Q3_K	21.0GB
Gabriel-8x7B-Instruct-v0.1.Q3_K_M.gguf	Q3_K_M	21.0GB
Gabriel-8x7B-Instruct-v0.1.Q3_K_L.gguf	Q3_K_L	22.51GB
Gabriel-8x7B-Instruct-v0.1.IQ4_XS.gguf	IQ4_XS	23.63GB
Gabriel-8x7B-Instruct-v0.1.Q4_0.gguf	Q4_0	24.63GB
Gabriel-8x7B-Instruct-v0.1.IQ4_NL.gguf	IQ4_NL	24.91GB
Gabriel-8x7B-Instruct-v0.1.Q4_K_S.gguf	Q4_K_S	24.91GB
Gabriel-8x7B-Instruct-v0.1.Q4_K.gguf	Q4_K	26.49GB
Gabriel-8x7B-Instruct-v0.1.Q4_K_M.gguf	Q4_K_M	26.49GB
Gabriel-8x7B-Instruct-v0.1.Q4_1.gguf	Q4_1	27.32GB
Gabriel-8x7B-Instruct-v0.1.Q5_0.gguf	Q5_0	30.02GB
Gabriel-8x7B-Instruct-v0.1.Q5_K_S.gguf	Q5_K_S	30.02GB
Gabriel-8x7B-Instruct-v0.1.Q5_K.gguf	Q5_K	30.95GB
Gabriel-8x7B-Instruct-v0.1.Q5_K_M.gguf	Q5_K_M	30.95GB
Gabriel-8x7B-Instruct-v0.1.Q5_1.gguf	Q5_1	32.71GB
Gabriel-8x7B-Instruct-v0.1.Q6_K.gguf	Q6_K	35.74GB
Gabriel-8x7B-Instruct-v0.1.Q8_0.gguf	Q8_0	46.22GB

Original model description:

library_name: transformers license: apache-2.0 language:

Gabriel-8x7B-Instruct-v0.1 is a fine tuned model using a 36k French/English Christian dataset (self made).

Base model used for training: Mixtral-8x7B-Instruct-v0.1