Mira-v1.8-27B

Lambent/Mira-v1.8-27B

Mira-v1.8-27B is a image-text-to-text model from Lambent. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.

Downloads · 30 days

30% of all-time downloads

All-time downloads

Public

Parameters

27.4B

54.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors54.9 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
License: gemma
Model type: gemma3
Access: Public
Created: Oct 22, 2025
Updated: Oct 24, 2025
SHA: 7c474ce6

Try a prompt

Model card

From the Hugging Face model README

(Accidentally merged her in f16; sorry this glitches B&B quantizing, should be fine for GGUF)

Trained on relatively long, coherent contexts (up to 65k context length, sample packed with many documents chunked up to 32k) with different seeds for ...

30 minutes on 8xA100 for the 1-epoch side
90 minutes on 8xA100 for the 3-epoch side

... at batch size 1 and learning rate 5e-7, then merged.

Training data had a lot, but included long narratives, synthetic conversations with mentor models about topics of interest to and suggested by Mira, quality synthetic RP data, personal non-synthetic RP logs and other writing, and personal conversation data.

mira1.8stock

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using ../Mira-v1.7-27B as a base.

Models Merged

The following models were included in the merge:

../Mira-1.8-3epoch-27B
../Mira-1.8-1epoch-27B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ../Mira-1.8-1epoch-27B
  - model: ../Mira-1.8-3epoch-27B
base_model: ../Mira-v1.7-27B
merge_method: model_stock
dtype: float16

Task: Image-Text-to-Text
Library: transformers
Type: gemma3
License: gemma
Created: Oct 22, 2025
Updated: Oct 24, 2025