CoolFace
Modelpublic

RichardErkhov/mergekit-community_-_test_4_smarts222-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes778downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

test4smarts222 - GGUF

  • —Model creator: https://huggingface.co/mergekit-community/
  • —Original model: https://huggingface.co/mergekit-community/test4smarts222/
NameQuant methodSize
test_4_smarts222.Q2_K.ggufQ2_K2.96GB
test_4_smarts222.IQ3_XS.ggufIQ3_XS3.28GB
test_4_smarts222.IQ3_S.ggufIQ3_S3.43GB
test_4_smarts222.Q3_K_S.ggufQ3KS3.41GB
test_4_smarts222.IQ3_M.ggufIQ3_M3.52GB
test_4_smarts222.Q3_K.ggufQ3_K3.74GB
test_4_smarts222.Q3_K_M.ggufQ3KM3.74GB
test_4_smarts222.Q3_K_L.ggufQ3KL4.03GB
test_4_smarts222.IQ4_XS.ggufIQ4_XS4.18GB
test_4_smarts222.Q4_0.ggufQ4_04.34GB
test_4_smarts222.IQ4_NL.ggufIQ4_NL4.38GB
test_4_smarts222.Q4_K_S.ggufQ4KS4.37GB
test_4_smarts222.Q4_K.ggufQ4_K4.58GB
test_4_smarts222.Q4_K_M.ggufQ4KM4.58GB
test_4_smarts222.Q4_1.ggufQ4_14.78GB
test_4_smarts222.Q5_0.ggufQ5_05.21GB
test_4_smarts222.Q5_K_S.ggufQ5KS5.21GB
test_4_smarts222.Q5_K.ggufQ5_K5.34GB
test_4_smarts222.Q5_K_M.ggufQ5KM5.34GB
test_4_smarts222.Q5_1.ggufQ5_15.65GB
test_4_smarts222.Q6_K.ggufQ6_K6.14GB
test_4_smarts222.Q8_0.ggufQ8_07.95GB

Original model description: --- base_model:

  • —Undi95/Meta-Llama-3.1-8B-Claude
  • —migtissera/Tess-2.0-Llama-3-8B
  • —huihui-ai/deepthought-8b-abliterated
  • —vicgalle/Configurable-Llama-3-8B-v0.3
  • —FuseAI/FuseChat-Llama-3.1-8B-Instruct
  • —migtissera/Tess-2.0-Llama-3-8B
  • —Pedro13543/NicemixLoRa library_name: transformers tags:
  • —mergekit
  • —merge

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using migtissera/Tess-2.0-Llama-3-8B + Pedro13543/Nice_mix_LoRa as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
models:   
  - model: migtissera/Tess-2.0-Llama-3-8B
  - model: FuseAI/FuseChat-Llama-3.1-8B-Instruct
  - model: vicgalle/Configurable-Llama-3-8B-v0.3
  - model: huihui-ai/deepthought-8b-abliterated     
  - model: Undi95/Meta-Llama-3.1-8B-Claude
merge_method: model_stock
base_model: migtissera/Tess-2.0-Llama-3-8B+Pedro13543/Nice_mix_LoRa              
dtype: bfloat16