chameleon-7b-GGUF

This repo contains GGUF files of the chameleon-7b model. These files can be used for inference using llama.cpp and derivative software such as ollama and LM Studio.

Note: The GGUF files do not include the image tokenizer (VQ-VAE model) and thus can only be used for text-only inference.

Downloads last month
26
GGUF
Model size
7.01B params
Architecture
chameleon

4-bit

16-bit

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.