MoshiVis v0.1
Collection
MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs
•
8 items
•
Updated
•
13
Please refer to the main model card
This model page contains the Moshika (female voice) model weights for the MLX backend of the MoshiVis repo,
in bfloat16,Q8 and Q4 formats. We provide the same model weights for other backends and quantization formats in the associated model collection.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for kyutai/moshika-vis-mlx
Base model
google/paligemma2-3b-pt-448