CoolFace
Modelpublic

RichardErkhov/Nitral-AI_-_Eris_PrimeV4.20-Vision-32k-7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes3.9kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Eris_PrimeV4.20-Vision-32k-7B - GGUF

  • —Model creator: https://huggingface.co/Nitral-AI/
  • —Original model: https://huggingface.co/Nitral-AI/Eris_PrimeV4.20-Vision-32k-7B/
NameQuant methodSize
Eris_PrimeV4.20-Vision-32k-7B.Q2_K.ggufQ2_K2.53GB
Eris_PrimeV4.20-Vision-32k-7B.IQ3_XS.ggufIQ3_XS2.81GB
Eris_PrimeV4.20-Vision-32k-7B.IQ3_S.ggufIQ3_S2.96GB
Eris_PrimeV4.20-Vision-32k-7B.Q3_K_S.ggufQ3KS2.95GB
Eris_PrimeV4.20-Vision-32k-7B.IQ3_M.ggufIQ3_M3.06GB
Eris_PrimeV4.20-Vision-32k-7B.Q3_K.ggufQ3_K3.28GB
Eris_PrimeV4.20-Vision-32k-7B.Q3_K_M.ggufQ3KM3.28GB
Eris_PrimeV4.20-Vision-32k-7B.Q3_K_L.ggufQ3KL3.56GB
Eris_PrimeV4.20-Vision-32k-7B.IQ4_XS.ggufIQ4_XS3.67GB
Eris_PrimeV4.20-Vision-32k-7B.Q4_0.ggufQ4_03.83GB
Eris_PrimeV4.20-Vision-32k-7B.IQ4_NL.ggufIQ4_NL3.87GB
Eris_PrimeV4.20-Vision-32k-7B.Q4_K_S.ggufQ4KS3.86GB
Eris_PrimeV4.20-Vision-32k-7B.Q4_K.ggufQ4_K4.07GB
Eris_PrimeV4.20-Vision-32k-7B.Q4_K_M.ggufQ4KM4.07GB
Eris_PrimeV4.20-Vision-32k-7B.Q4_1.ggufQ4_14.24GB
Eris_PrimeV4.20-Vision-32k-7B.Q5_0.ggufQ5_04.65GB
Eris_PrimeV4.20-Vision-32k-7B.Q5_K_S.ggufQ5KS4.65GB
Eris_PrimeV4.20-Vision-32k-7B.Q5_K.ggufQ5_K4.78GB
Eris_PrimeV4.20-Vision-32k-7B.Q5_K_M.ggufQ5KM4.78GB
Eris_PrimeV4.20-Vision-32k-7B.Q5_1.ggufQ5_15.07GB
Eris_PrimeV4.20-Vision-32k-7B.Q6_K.ggufQ6_K5.53GB
Eris_PrimeV4.20-Vision-32k-7B.Q8_0.ggufQ8_07.17GB

Original model description: --- base_model:

  • —l3utterfly/mistral-7b-v0.2-layla-v4
  • —Nitral-AI/ErisPrimeV4-Vision-32k-7B libraryname: transformers tags:
  • —mergekit
  • —merge license: other ---

image/png

Eris Prime: Version 4.20 "Blaze it" 32k Edition

"Eris decided to pick up some recreational hobbies that led her to become a bit unhinged i guess."

Quants Available Here Thanks to Lewdiculus: https://huggingface.co/Lewdiculous/Eris_PrimeV4.20-Vision-32k-7B-GGUF-IQ-Imatrix

Vision/multimodal capabilities:

If you want to use vision functionality:

  • —You must use the latest versions of Koboldcpp.

To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo.

  • —You can load the mmproj by using the corresponding section in the interface:

image/png