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 Vikhrmodels/Vikhr-7B-instruct_0.4 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Vikhrmodels/Vikhr-7B-instruct_0.4
  - model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo # Another RP Model trained on... stuff
    parameters:
      density: 0.4
      weight: 0.25
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot # Another RP / Storytelling Model
    parameters:
      density: 0.5
      weight: 0.3
  - model: maldv/badger-iota-llama-3-8b #Megamerge - Helps with General Knowledge
    parameters:
      density: 0.6
      weight: 0.35
  - model: Sao10K/L3-8B-Stheno-v3.2 # This is Stheno v3.2's Initial Name
    parameters:
      density: 0.7
      weight: 0.4
merge_method: ties
base_model: Vikhrmodels/Vikhr-7B-instruct_0.4
parameters:
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
Downloads last month
10
Safetensors
Model size
7.63B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mergekit-community/mergekit-ties-svasnwf