Quantization made by Richard Erkhov.

Mistral-7B-v0.1-signtensors-1-over-4 - GGUF

Model creator: https://huggingface.co/awnr/
Original model: https://huggingface.co/awnr/Mistral-7B-v0.1-signtensors-1-over-4/

Name	Quant method	Size
Mistral-7B-v0.1-signtensors-1-over-4.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-v0.1-signtensors-1-over-4.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-v0.1-signtensors-1-over-4.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-v0.1-signtensors-1-over-4.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-v0.1-signtensors-1-over-4.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-v0.1-signtensors-1-over-4.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-v0.1-signtensors-1-over-4.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-v0.1-signtensors-1-over-4.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-v0.1-signtensors-1-over-4.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-v0.1-signtensors-1-over-4.Q4_0.gguf	Q4_0	2.78GB
Mistral-7B-v0.1-signtensors-1-over-4.IQ4_NL.gguf	IQ4_NL	1.22GB
Mistral-7B-v0.1-signtensors-1-over-4.Q4_K_S.gguf	Q4_K_S	0.11GB
Mistral-7B-v0.1-signtensors-1-over-4.Q4_K.gguf	Q4_K	0.46GB
Mistral-7B-v0.1-signtensors-1-over-4.Q4_K_M.gguf	Q4_K_M	0.09GB
Mistral-7B-v0.1-signtensors-1-over-4.Q4_1.gguf	Q4_1	0.03GB
Mistral-7B-v0.1-signtensors-1-over-4.Q5_0.gguf	Q5_0	0.0GB
Mistral-7B-v0.1-signtensors-1-over-4.Q5_K_S.gguf	Q5_K_S	0.0GB
Mistral-7B-v0.1-signtensors-1-over-4.Q5_K.gguf	Q5_K	0.0GB
Mistral-7B-v0.1-signtensors-1-over-4.Q5_K_M.gguf	Q5_K_M	0.0GB
Mistral-7B-v0.1-signtensors-1-over-4.Q5_1.gguf	Q5_1	0.0GB
Mistral-7B-v0.1-signtensors-1-over-4.Q6_K.gguf	Q6_K	0.28GB
Mistral-7B-v0.1-signtensors-1-over-4.Q8_0.gguf	Q8_0	2.91GB

Original model description:

license: apache-2.0

Model Card for Model Mistral-7B-v0.1-1-over-4

I'm experimenting with the weight matrices in neural networks. This is a clone of Mistral-7B-v0.1 with some weight matrices replaced.

I'm interested in seeing how the adjustmenets affect performance on existing metrics.

Model Details

Research in progress! Demons could come out of your nose if you use this.

Model Description

A modification of mistralai/Mistral-7B-v0.1. Thanks to their team for sharing their model.

Modified by: Dr. Alex W. Neal Riasanovsky
Model type: pre-trained
Language(s) (NLP): English
License: Apache-2.0

Bias, Risks, and Limitations

Use your own risk. I have no idea what this model's biases and limitations are. I just want to see if the benchmark values are similar to those from Mistral-7B-v0.1. I am setting up a long computational experiment to test some ideas.