h2m_-_mhm-7b-v1.3-DPO-1-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
h2m_-_mhm-7b-v1.3-DPO-1-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

mhm-7b-v1.3-DPO-1 - GGUF

Model creator: https://huggingface.co/h2m/
Original model: https://huggingface.co/h2m/mhm-7b-v1.3-DPO-1/

Name	Quant method	Size
mhm-7b-v1.3-DPO-1.Q2_K.gguf	Q2_K	2.53GB
mhm-7b-v1.3-DPO-1.IQ3_XS.gguf	IQ3_XS	2.81GB
mhm-7b-v1.3-DPO-1.IQ3_S.gguf	IQ3_S	2.96GB
mhm-7b-v1.3-DPO-1.Q3_K_S.gguf	Q3_K_S	2.95GB
mhm-7b-v1.3-DPO-1.IQ3_M.gguf	IQ3_M	3.06GB
mhm-7b-v1.3-DPO-1.Q3_K.gguf	Q3_K	3.28GB
mhm-7b-v1.3-DPO-1.Q3_K_M.gguf	Q3_K_M	3.28GB
mhm-7b-v1.3-DPO-1.Q3_K_L.gguf	Q3_K_L	3.56GB
mhm-7b-v1.3-DPO-1.IQ4_XS.gguf	IQ4_XS	3.67GB
mhm-7b-v1.3-DPO-1.Q4_0.gguf	Q4_0	3.83GB
mhm-7b-v1.3-DPO-1.IQ4_NL.gguf	IQ4_NL	3.87GB
mhm-7b-v1.3-DPO-1.Q4_K_S.gguf	Q4_K_S	3.86GB
mhm-7b-v1.3-DPO-1.Q4_K.gguf	Q4_K	4.07GB
mhm-7b-v1.3-DPO-1.Q4_K_M.gguf	Q4_K_M	4.07GB
mhm-7b-v1.3-DPO-1.Q4_1.gguf	Q4_1	4.24GB
mhm-7b-v1.3-DPO-1.Q5_0.gguf	Q5_0	4.65GB
mhm-7b-v1.3-DPO-1.Q5_K_S.gguf	Q5_K_S	4.65GB
mhm-7b-v1.3-DPO-1.Q5_K.gguf	Q5_K	4.78GB
mhm-7b-v1.3-DPO-1.Q5_K_M.gguf	Q5_K_M	4.78GB
mhm-7b-v1.3-DPO-1.Q5_1.gguf	Q5_1	5.07GB
mhm-7b-v1.3-DPO-1.Q6_K.gguf	Q6_K	5.53GB
mhm-7b-v1.3-DPO-1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 language:

en

image/jpeg

A DPO fine tuned mhm-7b-v1.3 on Intel/orca_dpo_pairs

Based upon mistral. Created using dare_ties and models from openllm leaderboard. Over 3 merges involving 7 different models, this was the result.

Just an experiment.