metadata

base_model:
  - NurtureAI/neural-chat-7b-v3-1-16k
  - NousResearch/Hermes-2-Pro-Mistral-7B
library_name: transformers
tags:
  - mergekit
  - merge

Testing purpose only, seem it not good in Roleplaying 😢

You may want see this: https://huggingface.co/Alsebay/My_LLMs_Leaderboard

merge

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

GGUF version:

https://huggingface.co/Alsebay/Nutopia-7B-GGUF

Want more? Not what you're looking for? Imatrix and the rest of quantization model was made by mradermacher. Thank mradermacher for help. :) https://huggingface.co/mradermacher/Nutopia-7B-GGUF

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: NurtureAI/neural-chat-7b-v3-1-16k
        layer_range: [0, 32]
      - model: NousResearch/Hermes-2-Pro-Mistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: NurtureAI/neural-chat-7b-v3-1-16k
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16