CoolFace
Modelpublic

RichardErkhov/Elfrino_-_LiquidCrystal_V3-20B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes249downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LiquidCrystal_V3-20B - GGUF

  • —Model creator: https://huggingface.co/Elfrino/
  • —Original model: https://huggingface.co/Elfrino/LiquidCrystal_V3-20B/
NameQuant methodSize
LiquidCrystal_V3-20B.Q2_K.ggufQ2_K6.91GB
LiquidCrystal_V3-20B.Q3_K_S.ggufQ3KS8.06GB
LiquidCrystal_V3-20B.Q3_K.ggufQ3_K9.04GB
LiquidCrystal_V3-20B.Q3_K_M.ggufQ3KM9.04GB
LiquidCrystal_V3-20B.Q3_K_L.ggufQ3KL9.9GB
LiquidCrystal_V3-20B.IQ4_XS.ggufIQ4_XS10.01GB
LiquidCrystal_V3-20B.Q4_0.ggufQ4_010.52GB
LiquidCrystal_V3-20B.IQ4_NL.ggufIQ4_NL10.57GB
LiquidCrystal_V3-20B.Q4_K_S.ggufQ4KS10.59GB
LiquidCrystal_V3-20B.Q4_K.ggufQ4_K11.22GB
LiquidCrystal_V3-20B.Q4_K_M.ggufQ4KM11.22GB
LiquidCrystal_V3-20B.Q4_1.ggufQ4_111.67GB
LiquidCrystal_V3-20B.Q5_0.ggufQ5_012.83GB
LiquidCrystal_V3-20B.Q5_K_S.ggufQ5KS12.83GB
LiquidCrystal_V3-20B.Q5_K.ggufQ5_K13.18GB
LiquidCrystal_V3-20B.Q5_K_M.ggufQ5KM13.18GB
LiquidCrystal_V3-20B.Q5_1.ggufQ5_113.98GB
LiquidCrystal_V3-20B.Q6_K.ggufQ6_K15.28GB
LiquidCrystal_V3-20B.Q8_0.ggufQ8_019.79GB

Original model description: --- base_model:

  • —Undi95/PsyMedRP-v1-20B
  • —Elfrino/XwinXtended-20B library_name: transformers tags:
  • —mergekit
  • —merge

Warning: Cute crystaBots inside!

A merge between an ol' fav: Undi95/PsyMedRP-v1-20B

and:

An extended XwinLM: Elfrino/XwinXtended-20B

Early results look promising but more testing is needed....

##############################################################################################

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
slices:
  - sources:
      - model: Undi95/PsyMedRP-v1-20B
        layer_range: [0, 62]
      - model: Elfrino/XwinXtended-20B
        layer_range: [0, 62]
merge_method: slerp
base_model: Undi95/PsyMedRP-v1-20B
parameters:
  t:
    - filter: self_attn
      value: [0.8, 0.8, 0.9, 0.7, .8]
    - filter: mlp
      value: [.8, 0.8, 0.9, 0.8, .7]
    - value: 0.2
dtype: bfloat16