README.md

metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

out

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated as a base.

Models Merged

The following models were included in the merge:

• /mnt/bigly/fp16/Llama-3.1-Swallow-70B-v0.1
• /mnt/ue/fp16-2/Llama-3.1-70B-FLDx2
• /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3
• /mnt/bigly/fp16/Blossom-70B
• /mnt/bigly/fp16/Llama-3-70B-Base
• /mnt/bigly/fp16/llama-3-youko-70b
• /mnt/ue/fp16-2/ProgressGym-HistLlama3-70B-C020-pretrain-v0.1
• /mnt/bigly/fp16/Hermes-3-Llama-3.1-70B
• /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
• /mnt/bigly/fp16/Llama3-PBM-Nova-70B
• /mnt/bigly/fp16/MergedHistLlama-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /mnt/bigly/fp16/Blossom-70B
  - model: /mnt/ue/fp16-2/L3.3-70B-Euryale-v2.3
  - model: /mnt/bigly/fp16/Llama-3-70B-Base
  - model: /mnt/bigly/fp16/Llama-3-Taiwan-70B-Instruct
  - model: /mnt/bigly/fp16/llama-3-youko-70b
  - model: /mnt/bigly/fp16/MergedHistLlama-70B
  - model: /mnt/bigly/fp16/Llama-3.1-Swallow-70B-v0.1
  - model: /mnt/bigly/fp16/Llama3-PBM-Nova-70B
  - model: /mnt/ue/fp16-2/Llama-3.1-70B-FLDx2
  - model: /mnt/ue/fp16-2/ProgressGym-HistLlama3-70B-C020-pretrain-v0.1
  - model: /mnt/bigly/fp16/Hermes-3-Llama-3.1-70B
merge_method: model_stock
base_model: /mnt/ue/fp16-2/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
dtype: float16