Tarek07's picture
Add files using upload-large-folder tool
332c697 verified
|
raw
history blame
1.18 kB
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

PrimogentorSCE3

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

Merge Details

Merge Method

This model was merged using the SCE merge method using downloads/Llama-3.1-Nemotron-lorablated-70B as a base.

Models Merged

The following models were included in the merge:

  • downloads/Wayfarer-Large-70B-Llama-3.3
  • downloads/EVA-LLaMA-3.33-70B-v0.1
  • downloads/Negative_LLAMA_70B
  • downloads/L3.1-70B-Hanami-x1
  • downloads/70B-L3.3-Cirrus-x1
  • downloads/Anubis-70B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: downloads/L3.1-70B-Hanami-x1
  - model: downloads/70B-L3.3-Cirrus-x1
  - model: downloads/Wayfarer-Large-70B-Llama-3.3
  - model: downloads/Negative_LLAMA_70B
  - model: downloads/Anubis-70B-v1
  - model: downloads/EVA-LLaMA-3.33-70B-v0.1
merge_method: sce
base_model: downloads/Llama-3.1-Nemotron-lorablated-70B
parameters:
  select_topk: 0.17
out_dtype: bfloat16
tokenizer:
 source: downloads/Negative_LLAMA_70B