Downloads · 30 days
11
10% of all-time downloads
Lambent/Mira-v1.28-dpo
Mira-v1.28-dpo 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
11
10% of all-time downloads
All-time downloads
112
Public
Parameters
27.4B
54.9 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors54.9 GB · 100%
From the Hugging Face model README



This is a merge of pre-trained language models created using mergekit.
This model was merged using the Karcher Mean merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ../Mira-v1.28-wave+./Mira-v1.28-dpo-adapters/dpoq-1
- model: ../Mira-v1.28-wave+./Mira-v1.28-dpo-adapters/dpoq-2
- model: ../Mira-v1.28-wave+./Mira-v1.28-dpo-adapters/dpoq-3
- model: ../Mira-v1.28-wave
merge_method: karcher
dtype: bfloat16
# Notes: Can delete these, just tossing this info your way in case you find it relevant.
# Modernized version of the legacy tokenizer_source route for extra params like `pad_to_multiple_of`. Unless you're using it for another reason that's going over my head.
tokenizer:
source: "../Mira-v1.28-wave"
pad_to_multiple_of: 16