slim-nli-tool / README.md
doberst's picture
Upload 3 files
bb0a108 verified
|
raw
history blame
1.91 kB
metadata
license: apache-2.0

Model Card for Model ID

slim-sentiment-tool is part of the SLIM ("Structured Language Instruction Model") model series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.

slim-sentiment-tool is a 4_K_M quantized GGUF version of slim-sentiment-tool, providing a fast, small inference implementation.

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

from llmware.models import ModelCatalog

sentiment_tool = ModelCatalog().load_model("llmware/slim-sentiment-tool")
response = sentiment_tool.function_call(text_sample, params=["sentiment"], function="classify")

Slim models can also be loaded even more simply as part of LLMfx calls:

from llmware.agents import LLMfx

llm_fx = LLMfx()
llm_fx.load_tool("sentiment")
response = llm_fx.sentiment(text)

Model Description

  • Developed by: llmware
  • Model type: GGUF
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Quantized from model: llmware/slim-sentiment (finetuned tiny llama)

Uses

The intended use of SLIM models is to re-imagine traditional 'hard-coded' classifiers through the use of function calls.

Example:

text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."   

model generation - {"sentiment": ["negative"]}

keys = "sentiment"

All of the SLIM models use a novel prompt instruction structured as follows:

"<human> " + text + "<classify> " + keys + "</classify>" + "/n<bot>: "

Model Card Contact

Darren Oberst & llmware team