cloudyu_-_Mixtral_7Bx5_MoE_30B_DPO-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
cloudyu_-_Mixtral_7Bx5_MoE_30B_DPO-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Mixtral_7Bx5_MoE_30B_DPO - GGUF

Model creator: https://huggingface.co/cloudyu/
Original model: https://huggingface.co/cloudyu/Mixtral_7Bx5_MoE_30B_DPO/

Name	Quant method	Size
Mixtral_7Bx5_MoE_30B_DPO.Q2_K.gguf	Q2_K	10.14GB
Mixtral_7Bx5_MoE_30B_DPO.IQ3_XS.gguf	IQ3_XS	11.35GB
Mixtral_7Bx5_MoE_30B_DPO.IQ3_S.gguf	IQ3_S	11.99GB
Mixtral_7Bx5_MoE_30B_DPO.Q3_K_S.gguf	Q3_K_S	11.97GB
Mixtral_7Bx5_MoE_30B_DPO.IQ3_M.gguf	IQ3_M	12.2GB
Mixtral_7Bx5_MoE_30B_DPO.Q3_K.gguf	Q3_K	13.29GB
Mixtral_7Bx5_MoE_30B_DPO.Q3_K_M.gguf	Q3_K_M	13.29GB
Mixtral_7Bx5_MoE_30B_DPO.Q3_K_L.gguf	Q3_K_L	14.39GB
Mixtral_7Bx5_MoE_30B_DPO.IQ4_XS.gguf	IQ4_XS	14.97GB
Mixtral_7Bx5_MoE_30B_DPO.Q4_0.gguf	Q4_0	15.64GB
Mixtral_7Bx5_MoE_30B_DPO.IQ4_NL.gguf	IQ4_NL	15.79GB
Mixtral_7Bx5_MoE_30B_DPO.Q4_K_S.gguf	Q4_K_S	15.78GB
Mixtral_7Bx5_MoE_30B_DPO.Q4_K.gguf	Q4_K	16.79GB
Mixtral_7Bx5_MoE_30B_DPO.Q4_K_M.gguf	Q4_K_M	16.79GB
Mixtral_7Bx5_MoE_30B_DPO.Q4_1.gguf	Q4_1	17.37GB
Mixtral_7Bx5_MoE_30B_DPO.Q5_0.gguf	Q5_0	19.09GB
Mixtral_7Bx5_MoE_30B_DPO.Q5_K_S.gguf	Q5_K_S	19.09GB
Mixtral_7Bx5_MoE_30B_DPO.Q5_K.gguf	Q5_K	19.68GB
Mixtral_7Bx5_MoE_30B_DPO.Q5_K_M.gguf	Q5_K_M	19.68GB
Mixtral_7Bx5_MoE_30B_DPO.Q5_1.gguf	Q5_1	20.82GB
Mixtral_7Bx5_MoE_30B_DPO.Q6_K.gguf	Q6_K	22.76GB
Mixtral_7Bx5_MoE_30B_DPO.Q8_0.gguf	Q8_0	29.48GB

Original model description:

license: mit tags:

moe

This is DPO improved version of cloudyu/Mixtral_7Bx5_MoE_30B
DPO Trainer
metric not test