Xiaojian9992024/Llama3.1-8B-Dyanka-Preview

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 nvidia/Llama-3.1-Nemotron-Nano-8B-v1 as a base.

Models Merged

The following models were included in the merge:

• SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
• s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1
• OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09
• grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
• DeepAuto-AI/Explore_Llama-3.1-8B-Inst
• FreedomIntelligence/HuatuoGPT-o1-8B
• HiTZ/Latxa-Llama-3.1-8B-Instruct
• prithivMLmods/Llama-3.1-8B-Open-SFT
• passing2961/Thanos-8B
• arcee-ai/Llama-3.1-SuperNova-Lite

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nvidia/Llama-3.1-Nemotron-Nano-8B-v1
    #no parameters necessary for base model
  - model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
    parameters:
      density: 0.1
      weight: 0.1
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      density: 0.1
      weight: 0.1
  - model: passing2961/Thanos-8B
    parameters:
      density: 0.1
      weight: 0.1
  - model: prithivMLmods/Llama-3.1-8B-Open-SFT
    parameters:
      density: 0.1
      weight: 0.1
  - model: FreedomIntelligence/HuatuoGPT-o1-8B
    parameters:
      density: 0.1
      weight: 0.1
  - model: s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1
    parameters:
      density: 0.1
      weight: 0.1
  - model: HiTZ/Latxa-Llama-3.1-8B-Instruct
    parameters:
      density: 0.1
      weight: 0.1
  - model: grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
    parameters:
      density: 0.1
      weight: 0.1
  - model: DeepAuto-AI/Explore_Llama-3.1-8B-Inst
    parameters:
      density: 0.1
      weight: 0.1
  - model: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09
    parameters:
      density: 0.1
      weight: 0.1
merge_method: ties
base_model: nvidia/Llama-3.1-Nemotron-Nano-8B-v1
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16