RichardErkhov/S4sch_-_Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b-gguf

Quantization made by Richard Erkhov.

Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b - GGUF

Model creator: https://huggingface.co/S4sch/
Original model: https://huggingface.co/S4sch/Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b/

Name	Quant method	Size
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q2_K.gguf	Q2_K	3.95GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.IQ3_XS.gguf	IQ3_XS	4.39GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.IQ3_S.gguf	IQ3_S	4.63GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q3_K_S.gguf	Q3_K_S	4.61GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.IQ3_M.gguf	IQ3_M	4.78GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q3_K.gguf	Q3_K	5.13GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q3_K_M.gguf	Q3_K_M	5.13GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q3_K_L.gguf	Q3_K_L	5.58GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.IQ4_XS.gguf	IQ4_XS	5.75GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q4_0.gguf	Q4_0	6.0GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.IQ4_NL.gguf	IQ4_NL	6.06GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q4_K_S.gguf	Q4_K_S	6.04GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q4_K.gguf	Q4_K	6.38GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q4_K_M.gguf	Q4_K_M	6.38GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q4_1.gguf	Q4_1	6.65GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q5_0.gguf	Q5_0	7.31GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q5_K_S.gguf	Q5_K_S	7.31GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q5_K.gguf	Q5_K	7.5GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q5_K_M.gguf	Q5_K_M	7.5GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q5_1.gguf	Q5_1	7.96GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q6_K.gguf	Q6_K	8.7GB
Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b.Q8_0.gguf	Q8_0	11.27GB

Original model description:

license: apache-2.0

Frankenmerge 11b between teknium/OpenHermes-2.5-Mistral-7B and Intel/neural-chat-7b-v3-1

GGUF: https://huggingface.co/TheBloke/Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b-GGUF

Merge with the following conditions

  - model: teknium/OpenHermes-2.5-Mistral-7B
    layer_range: [0, 8]

  - model: Intel/neural-chat-7b-v3-1
    layer_range: [4, 12]

  - model: teknium/OpenHermes-2.5-Mistral-7B
    layer_range: [9, 16]

  - model: Intel/neural-chat-7b-v3-1
    layer_range: [13, 20]

  - model: teknium/OpenHermes-2.5-Mistral-7B
    layer_range: [17, 24]

  - model: Intel/neural-chat-7b-v3-1
    layer_range: [21, 28]

  - model: teknium/OpenHermes-2.5-Mistral-7B
    layer_range: [25, 32]

merge_method: passthrough

Benchmarks are coming soon...