llmware/slim-topics

SLIM-TOPICS

<!-- Provide a quick summary of what the model is/does. -->

slim-topics is part of the SLIM ("Structured Language Instruction Model") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.

slim-sentiment has been fine-tuned for topic analysis function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:

&nbsp;&nbsp;&nbsp;&nbsp;{"topics": ["..."]}

SLIM models are designed to generate structured outputs that can be used programmatically as part of a multi-step, multi-model LLM-based automation workflow.

Each slim model has a 'quantized tool' version, e.g., **'slim-topics-tool'**.

Prompt format:

function = "classify" params = "topics" prompt = "<human> " + {text} + "\n" + &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;"<{function}> " + {params} + "</{function}>" + "\n<bot>:"

<details> <summary>Transformers Script </summary>

model = AutoModelForCausalLM.frompretrained("llmware/slim-topics") tokenizer = AutoTokenizer.frompretrained("llmware/slim-topics")

function = "classify" params = "topic"

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

prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"

inputs = tokenizer(prompt, returntensors="pt") startofinput = len(inputs.inputids[0])

outputs = model.generate( inputs.inputids.to('cpu'), eostokenid=tokenizer.eostokenid, padtokenid=tokenizer.eostokenid, dosample=True, temperature=0.3, maxnewtokens=100 )

outputonly = tokenizer.decode(outputs[0][startofinput:], skipspecial_tokens=True)

print("output only: ", output_only)

# here's the fun part try: outputonly = ast.literaleval(llmstringoutput) print("success - converted to python dictionary automatically") except: print("fail - could not convert to python dictionary automatically - ", llmstringoutput)

</details>

<details>

<summary>Using as Function Call in LLMWare</summary>

from llmware.models import ModelCatalog slimmodel = ModelCatalog().loadmodel("llmware/slim-topics") response = slimmodel.functioncall(text,params=["topics"], function="classify")

print("llmware - llm_response: ", response)

</details>

Model Card Contact

Darren Oberst & llmware team

Join us on Discord