You can deploy this model and start earning money today!

RichardErkhov/
mergekit-community_-_final_test_4_original_old_recipe-gguf

Name: mergekit-community_-_final_test_4_original_old_recipe-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

final_test_4_original_old_recipe - GGUF

Model creator: https://huggingface.co/mergekit-community/
Original model: https://huggingface.co/mergekit-community/final_test_4_original_old_recipe/

Name	Quant method	Size
final_test_4_original_old_recipe.Q2_K.gguf	Q2_K	2.96GB
final_test_4_original_old_recipe.IQ3_XS.gguf	IQ3_XS	3.28GB
final_test_4_original_old_recipe.IQ3_S.gguf	IQ3_S	3.43GB
final_test_4_original_old_recipe.Q3_K_S.gguf	Q3_K_S	3.41GB
final_test_4_original_old_recipe.IQ3_M.gguf	IQ3_M	3.52GB
final_test_4_original_old_recipe.Q3_K.gguf	Q3_K	3.74GB
final_test_4_original_old_recipe.Q3_K_M.gguf	Q3_K_M	3.74GB
final_test_4_original_old_recipe.Q3_K_L.gguf	Q3_K_L	4.03GB
final_test_4_original_old_recipe.IQ4_XS.gguf	IQ4_XS	4.18GB
final_test_4_original_old_recipe.Q4_0.gguf	Q4_0	4.34GB
final_test_4_original_old_recipe.IQ4_NL.gguf	IQ4_NL	4.38GB
final_test_4_original_old_recipe.Q4_K_S.gguf	Q4_K_S	4.37GB
final_test_4_original_old_recipe.Q4_K.gguf	Q4_K	4.58GB
final_test_4_original_old_recipe.Q4_K_M.gguf	Q4_K_M	4.58GB
final_test_4_original_old_recipe.Q4_1.gguf	Q4_1	4.78GB
final_test_4_original_old_recipe.Q5_0.gguf	Q5_0	5.21GB
final_test_4_original_old_recipe.Q5_K_S.gguf	Q5_K_S	5.21GB
final_test_4_original_old_recipe.Q5_K.gguf	Q5_K	5.34GB
final_test_4_original_old_recipe.Q5_K_M.gguf	Q5_K_M	5.34GB
final_test_4_original_old_recipe.Q5_1.gguf	Q5_1	5.65GB
final_test_4_original_old_recipe.Q6_K.gguf	Q6_K	6.14GB
final_test_4_original_old_recipe.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

Solshine/reflection-llama-3.1-8B
vicgalle/Humanish-Roleplay-Llama-3.1-8B
Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3 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 della_linear merge method using Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 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: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
    parameters:
      density: 0.5
      weight: 0.5
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: Solshine/reflection-llama-3.1-8B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: della_linear
base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
parameters:
  normalize: false
  int8_mask: true
dtype: float16

RichardErkhov/mergekit-community_-_final_test_4_original_old_recipe-gguf