SLIM GGUF
Collection
Quantized GGUF 'tool' implementations of SLIM Models
•
30 items
•
Updated
•
9
slim-ratings-tool is a 4_K_M 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 huggingface_hub import snapshot_download
snapshot_download("llmware/slim-ratings-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-ratings-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-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
llm_fx = LLMfx()
llm_fx.load_tool("ratings")
response = llm_fx.ratings(text)
Note: please review config.json in the repository for prompt wrapping information, details on the model, and full test set.
Darren Oberst & llmware team