RichardErkhov/cgato_-_TheSpice-7b-FT-ExperimentalOrca-gguf

Quantization made by Richard Erkhov.

TheSpice-7b-FT-ExperimentalOrca - GGUF

Model creator: https://huggingface.co/cgato/
Original model: https://huggingface.co/cgato/TheSpice-7b-FT-ExperimentalOrca/

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

Original model description:

license: cc-by-nc-4.0

A smort model made using the cleaned Orca data.

{System Prompt}

Username: {Input}
BotName: {Response}
Username: {Input}
BotName: {Response}

Seriously, I have to add more due to HF Leaderboard requirements. so basically, this model uses a cleaned version of Orca along with my typical RP data package. It was intended as a test to see if the models RP evals would be affected by an overwhelming amount of instruct tokens.