emissions-extraction-lora merged with the mistralai/Mistral-7B-Instruct-v0.2, converted into GGUF format and quantized. Can be used with llama.cpp.

GGUF

Model size

7.24B params

Architecture

llama

5-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Collection including nopperl/emissions-extraction-lora-merged-GGUF