These are quantized version of the BakLLaVA model to be used with llama.cpp and Python bindings (llama-cpp-python and PyLLMCore).

The original model card is available here: https://huggingface.co/SkunkworksAI/BakLLaVA-1

Downloads last month
41
GGUF
Model size
312M params
Architecture
clip

4-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.