Theros/llama3.2-CharReflectBase-3B

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using ericflo/Llama-3.2-3B-COT as a base.

Models Merged

The following models were included in the merge:

• Orion-zhen/Reflection-Llama3.2-3B-Instruct
• chuanli11/Llama-3.2-3B-Instruct-uncensored + bunnycore/Llama-3.2-3B-RP-LORA
• ericflo/Llama-3.2-3B-COT + bunnycore/Llama-3.2-3B-General-lora_model

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Orion-zhen/Reflection-Llama3.2-3B-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: ericflo/Llama-3.2-3B-COT+bunnycore/Llama-3.2-3B-General-lora_model
    parameters:
      density: 0.2
      weight: 0.2
  - model: chuanli11/Llama-3.2-3B-Instruct-uncensored+bunnycore/Llama-3.2-3B-RP-LORA
    parameters:
      density: 0.3
      weight: 0.3
merge_method: ties
base_model: ericflo/Llama-3.2-3B-COT
parameters:
  density: 1
  normalize: false
  int8_mask: true
dtype: float16