RichardErkhov/Weyaxi_-_neural-chat-7b-v3-1-OpenHermes-2.5-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

neural-chat-7b-v3-1-OpenHermes-2.5-7B - GGUF

• Model creator: https://huggingface.co/Weyaxi/
• Original model: https://huggingface.co/Weyaxi/neural-chat-7b-v3-1-OpenHermes-2.5-7B/

Name	Quant method	Size
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q2_K.gguf	Q2_K	2.53GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.IQ3_S.gguf	IQ3_S	2.96GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.IQ3_M.gguf	IQ3_M	3.06GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q3_K.gguf	Q3_K	3.28GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q4_0.gguf	Q4_0	3.83GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q4_K.gguf	Q4_K	4.07GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q4_1.gguf	Q4_1	4.24GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q5_0.gguf	Q5_0	4.65GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q5_K.gguf	Q5_K	4.78GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q5_1.gguf	Q5_1	5.07GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q6_K.gguf	Q6_K	5.53GB
neural-chat-7b-v3-1-OpenHermes-2.5-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0

Merge of Intel/neural-chat-7b-v3-1 and teknium/OpenHermes-2.5-Mistral-7B using ties merge.

Weights

• Intel/neural-chat-7b-v3-1: 0.5

• teknium/OpenHermes-2.5-Mistral-7B: 0.3

Density

• Intel/neural-chat-7b-v3-1: 0.5

• teknium/OpenHermes-2.5-Mistral-7B: 0.5