llmware/slim-ratings-tool
SLIM-RATINGS
<!-- Provide a quick summary of what the model is/does. -->
slim-ratings-tool is a 4KM quantized GGUF version of slim-sentiment, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
**slim-ratings** is part of the SLIM ("Structured Language Instruction Model") series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.
To pull the model via API:
from huggingfacehub import snapshotdownload snapshotdownload("llmware/slim-ratings-tool", localdir="/path/on/your/machine/", localdiruse_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().loadmodel("slim-ratings-tool") response = model.functioncall(text_sample)
# this one line will download the model and run a series of tests ModelCatalog().tooltestrun("slim-ratings-tool", verbose=True)
Slim models can also be loaded even more simply as part of a multi-model, multi-step LLMfx calls:
from llmware.agents import LLMfx
llmfx = LLMfx() llmfx.loadtool("ratings") response = llmfx.ratings(text)
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