Casual-Autopsy

Artoma-Lexicon-31B

Deploy Dedicated

README

License: apache-2.0

Merge Details

Merge Method

This model was merged using the DELLA and Model Breadcrumbs with TIES merge methods using gemma-4-31B-it as the base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configurations were used to produce this model:

yaml

# Step 1 models:  - model: TheDrummer/Artemis-31B-v1.2    parameters:      density: 1      weight: 1      epsilon: 0  - model: ReadyArt/gemma-4-31B-it-scotoma    parameters:      density: 0.45      weight: 0.2      epsilon: 0.25 base_model: google/gemma-4-31B-itmerge_method: della parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16 name: Artoma-31B

yaml

# Step 2 models:  - model: LatitudeGames/Equinox-31B    parameters:      weight: 0.4      density: 0.65      gamma: 0.02  - model: nbeerbower/Gemma4-Gutenberg-31B    parameters:      weight: 0.2      density: 0.35      gamma: 0.01  - model: MRockatansky/Gemma-4-31B-storymaxxed    parameters:      weight: 0.2      density: 0.35      gamma: 0.01 base_model: Artoma-31Bmerge_method: breadcrumbs_ties parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Model Details

Model Provider

Casual-Autopsy

Model Tree

Base

ReadyArt/gemma-4-31B-it-scotoma

Base

LatitudeGames/Equinox-31B

Base

nbeerbower/Gemma4-Gutenberg-31B

Base

TheDrummer/Artemis-31B-v1.2

Base

google/gemma-4-31B-it

Base

MRockatansky/Gemma-4-31B-storymaxxed

Merged

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Merge Details

Merge Method

This model was merged using the DELLA and Model Breadcrumbs with TIES merge methods using gemma-4-31B-it as the base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configurations were used to produce this model:

yaml

# Step 1 models:  - model: TheDrummer/Artemis-31B-v1.2    parameters:      density: 1      weight: 1      epsilon: 0  - model: ReadyArt/gemma-4-31B-it-scotoma    parameters:      density: 0.45      weight: 0.2      epsilon: 0.25 base_model: google/gemma-4-31B-itmerge_method: della parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16 name: Artoma-31B

# Step 1 models:  - model: TheDrummer/Artemis-31B-v1.2    parameters:      density: 1      weight: 1      epsilon: 0  - model: ReadyArt/gemma-4-31B-it-scotoma    parameters:      density: 0.45      weight: 0.2      epsilon: 0.25 base_model: google/gemma-4-31B-itmerge_method: della parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16 name: Artoma-31B

yaml

# Step 2 models:  - model: LatitudeGames/Equinox-31B    parameters:      weight: 0.4      density: 0.65      gamma: 0.02  - model: nbeerbower/Gemma4-Gutenberg-31B    parameters:      weight: 0.2      density: 0.35      gamma: 0.01  - model: MRockatansky/Gemma-4-31B-storymaxxed    parameters:      weight: 0.2      density: 0.35      gamma: 0.01 base_model: Artoma-31Bmerge_method: breadcrumbs_ties parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16

# Step 2 models:  - model: LatitudeGames/Equinox-31B    parameters:      weight: 0.4      density: 0.65      gamma: 0.02  - model: nbeerbower/Gemma4-Gutenberg-31B    parameters:      weight: 0.2      density: 0.35      gamma: 0.01  - model: MRockatansky/Gemma-4-31B-storymaxxed    parameters:      weight: 0.2      density: 0.35      gamma: 0.01 base_model: Artoma-31Bmerge_method: breadcrumbs_ties parameters:  normalize: true  int8_mask: false dtype: float32out_dtype: bfloat16