ApocalypseParty

G4-31B-TIES-Triple

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

Merge Details

Merge Method

This model was merged using the TIES merge method using google/gemma-4-31B-it as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
merge_method: ties
base_model: google/gemma-4-31B-it
models:
  - model: ApocalypseParty/G4-31B-ASFT-Test-1
    parameters:
      weight: 0.4
      density: 0.7
  - model: ApocalypseParty/G4-31B-DFT-Test-2-chkpt120
    parameters:
      weight: 0.3
      density: 0.7
  - model: zerofata/G4-MeroMero-31B
    parameters:
      weight: 0.3
      density: 0.7
dtype: bfloat16

Model provider

ApocalypseParty

Model tree

Base

zerofata/G4-MeroMero-31B

Base

ApocalypseParty/G4-31B-ASFT-Test-1

Base

google/gemma-4-31B-it

Base

ApocalypseParty/G4-31B-DFT-Test-2-chkpt120

Merged

this model

Modalities

Input

Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

G4-31B-TIES-Triple

Get help setting up a custom Dedicated Endpoints.

Merge Details

Merge Method

Models Merged

Configuration

Explore FriendliAI today