RichardErkhov/cloudyu_-_Phoenix_DPO_60B-gguf

Quantization made by Richard Erkhov.

Phoenix_DPO_60B - GGUF

Model creator: https://huggingface.co/cloudyu/
Original model: https://huggingface.co/cloudyu/Phoenix_DPO_60B/

Name	Quant method	Size
Phoenix_DPO_60B.Q2_K.gguf	Q2_K	20.86GB
Phoenix_DPO_60B.IQ3_XS.gguf	IQ3_XS	23.26GB
Phoenix_DPO_60B.IQ3_S.gguf	IQ3_S	24.56GB
Phoenix_DPO_60B.Q3_K_S.gguf	Q3_K_S	24.51GB
Phoenix_DPO_60B.IQ3_M.gguf	IQ3_M	25.2GB
Phoenix_DPO_60B.Q3_K.gguf	Q3_K	27.23GB
Phoenix_DPO_60B.Q3_K_M.gguf	Q3_K_M	27.23GB
Phoenix_DPO_60B.Q3_K_L.gguf	Q3_K_L	29.59GB
Phoenix_DPO_60B.IQ4_XS.gguf	IQ4_XS	30.58GB
Phoenix_DPO_60B.Q4_0.gguf	Q4_0	31.98GB
Phoenix_DPO_60B.IQ4_NL.gguf	IQ4_NL	32.27GB
Phoenix_DPO_60B.Q4_K_S.gguf	Q4_K_S	32.22GB
Phoenix_DPO_60B.Q4_K.gguf	Q4_K	34.14GB
Phoenix_DPO_60B.Q4_K_M.gguf	Q4_K_M	34.14GB
Phoenix_DPO_60B.Q4_1.gguf	Q4_1	35.49GB
Phoenix_DPO_60B.Q5_0.gguf	Q5_0	39.0GB
Phoenix_DPO_60B.Q5_K_S.gguf	Q5_K_S	39.0GB
Phoenix_DPO_60B.Q5_K.gguf	Q5_K	40.12GB
Phoenix_DPO_60B.Q5_K_M.gguf	Q5_K_M	40.12GB
Phoenix_DPO_60B.Q5_1.gguf	Q5_1	42.51GB
Phoenix_DPO_60B.Q6_K.gguf	Q6_K	46.47GB
Phoenix_DPO_60B.Q8_0.gguf	Q8_0	60.18GB

Original model description:

license: other tags: - yi - moe license_name: yi-license license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE

this is a DPO fine-tuned MoE model with 60B parameter.

DPO Trainer
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.

GGUF format is ready at cloudyu/Phoenix_DPO_60B_gguf