SLIM-SUMMARY-TINY-TOOL

slim-summary-tiny-tool is a 4_K_M quantized GGUF version of slim-summary-tiny, providing a small, fast inference implementation, to provide high-quality summarizations of complex business documents, on a small, specialized locally-deployable model with summary output structured as a python list of key points.

The size of the self-contained GGUF model binary is ~700 MB, which is small enough to run locally on a CPU with reasonable inference speed, and has been designed to balance solid quality with fast loading and inference on a local machine.

The model takes as input a text passage, an optional parameter with a focusing phrase or query, and an experimental optional (N) parameter, which is used to guide the model to a specific number of items return in a summary list.

Please see the usage notes at: slim-summary-tiny

To pull the model via API:

from huggingface_hub import snapshot_download           
snapshot_download("llmware/slim-summary-tiny-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)  

Load in your favorite GGUF inference engine, or try with llmware as follows:

from llmware.models import ModelCatalog  

# to load the model and make a basic inference
model = ModelCatalog().load_model("slim-summary-tiny-tool")
response = model.function_call(text_sample)  

# this one line will download the model and run a series of tests
ModelCatalog().tool_test_run("slim-summary-tiny-tool", verbose=True)  

Note: please review config.json in the repository for prompt wrapping information, details on the model, and full test set.

Model Card Contact

Darren Oberst & llmware team

Any questions? Join us on Discord