Name	Quant method	Size
LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf	Q2_K	2.96GB
LLama-3.1-8b-Ultra-Max-Pro.IQ3_XS.gguf	IQ3_XS	3.28GB
LLama-3.1-8b-Ultra-Max-Pro.IQ3_S.gguf	IQ3_S	3.43GB
LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf	Q3_K_S	3.41GB
LLama-3.1-8b-Ultra-Max-Pro.IQ3_M.gguf	IQ3_M	3.52GB
LLama-3.1-8b-Ultra-Max-Pro.Q3_K.gguf	Q3_K	3.74GB
LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf	Q3_K_M	3.74GB
LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf	Q3_K_L	4.03GB
LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf	IQ4_XS	4.18GB
LLama-3.1-8b-Ultra-Max-Pro.Q4_0.gguf	Q4_0	4.34GB
LLama-3.1-8b-Ultra-Max-Pro.IQ4_NL.gguf	IQ4_NL	4.38GB
LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf	Q4_K_S	4.37GB
LLama-3.1-8b-Ultra-Max-Pro.Q4_K.gguf	Q4_K	4.58GB
LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf	Q4_K_M	4.58GB
LLama-3.1-8b-Ultra-Max-Pro.Q4_1.gguf	Q4_1	4.78GB
LLama-3.1-8b-Ultra-Max-Pro.Q5_0.gguf	Q5_0	5.21GB
LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf	Q5_K_S	5.21GB
LLama-3.1-8b-Ultra-Max-Pro.Q5_K.gguf	Q5_K	5.34GB
LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf	Q5_K_M	5.34GB
LLama-3.1-8b-Ultra-Max-Pro.Q5_1.gguf	Q5_1	5.65GB
LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf	Q6_K	6.14GB
LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

AGI-0/Artificium-llama3.1-8B-001
Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
vicgalle/Configurable-Llama-3.1-8B-Instruct
Dampfinchen/Llama-3.1-8B-Ultra-Instruct
NousResearch/Hermes-3-Llama-3.1-8B
bunnycore/LLama-3.1-Hyper-Stock 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 DARE TIES merge method using vicgalle/Configurable-Llama-3.1-8B-Instruct 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: Dampfinchen/Llama-3.1-8B-Ultra-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/LLama-3.1-Hyper-Stock
    parameters:
      density: 0.5
      weight: 0.5
  - model: AGI-0/Artificium-llama3.1-8B-001
    parameters:
      density: 0.5
      weight: 0.5
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.5
      weight: 0.5
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: float16

RichardErkhov/bunnycore_-_LLama-3.1-8b-Ultra-Max-Pro-gguf