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 Linear DELLA merge method using models/gemma-4-31B-it as a base.

Models Merged

The following models were included in the merge:

  • models/gemma-4-31B
  • models/G4-MeroMero-31B-uncensored-heretic
  • models/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic
  • models/Gemma4-GarnetV2-31B

Configuration

The following YAML configuration was used to produce this model:

yaml

architecture: Gemma4ForConditionalGeneration
base_model: models/gemma-4-31B-it
models:
- model: models/gemma-4-31B
parameters:
weight: 0.2
- model: models/gemma-4-31B-it
parameters:
weight: 0.2
- model: models/G4-MeroMero-31B-uncensored-heretic
parameters:
weight: 0.2
- model: models/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic
parameters:
weight: 0.2
- model: models/Gemma4-GarnetV2-31B
parameters:
weight: 0.2
merge_method: della_linear
parameters:
lambda: 1.0
normalize: false
int8_mask: false
rescale: true
density: 0.5
epsilon: 0.4
dtype: bfloat16
out_dtype: bfloat16
tokenizer:
source: union
chat_template: auto

Model provider

sheliak

sheliak

Model tree

Base

this model

Modalities

Input

Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today