Modelpublic

RichardErkhov/Legalaz_-_04_llambo1_22_14-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes882downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

04llambo122_14 - GGUF

—Model creator: https://huggingface.co/Legalaz/
—Original model: https://huggingface.co/Legalaz/04llambo122_14/

Name	Quant method	Size
04_llambo1_22_14.Q2_K.gguf	Q2_K	2.96GB
04_llambo1_22_14.IQ3_XS.gguf	IQ3_XS	3.28GB
04_llambo1_22_14.IQ3_S.gguf	IQ3_S	3.43GB
04_llambo1_22_14.Q3_K_S.gguf	Q3KS	3.41GB
04_llambo1_22_14.IQ3_M.gguf	IQ3_M	3.52GB
04_llambo1_22_14.Q3_K.gguf	Q3_K	3.74GB
04_llambo1_22_14.Q3_K_M.gguf	Q3KM	3.74GB
04_llambo1_22_14.Q3_K_L.gguf	Q3KL	4.03GB
04_llambo1_22_14.IQ4_XS.gguf	IQ4_XS	4.18GB
04_llambo1_22_14.Q4_0.gguf	Q4_0	4.34GB
04_llambo1_22_14.IQ4_NL.gguf	IQ4_NL	4.38GB
04_llambo1_22_14.Q4_K_S.gguf	Q4KS	4.37GB
04_llambo1_22_14.Q4_K.gguf	Q4_K	4.58GB
04_llambo1_22_14.Q4_K_M.gguf	Q4KM	4.58GB
04_llambo1_22_14.Q4_1.gguf	Q4_1	4.78GB
04_llambo1_22_14.Q5_0.gguf	Q5_0	5.21GB
04_llambo1_22_14.Q5_K_S.gguf	Q5KS	5.21GB
04_llambo1_22_14.Q5_K.gguf	Q5_K	5.34GB
04_llambo1_22_14.Q5_K_M.gguf	Q5KM	5.34GB
04_llambo1_22_14.Q5_1.gguf	Q5_1	5.65GB
04_llambo1_22_14.Q6_K.gguf	Q6_K	6.14GB
04_llambo1_22_14.Q8_0.gguf	Q8_0	7.95GB

Original model description: --- basemodel: [] libraryname: transformers tags:

—mergekit
—merge

top

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

—/root/top1
—/root/top2

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: /root/top2
    parameters:
      weight: 0.8972
  - model: /root/top1
    parameters:
      weight: 0.0628
merge_method: linear
dtype: bfloat16