SLIM-Q-GEN-PHI-3-TOOL

slim-q-gen-phi-3 is a 4_K_M quantized GGUF version of slim-q-gen-phi-3, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.

This model implements a generative 'question' (e.g., 'q-gen') function, which takes a context passage as an input, and then generates as an output a python dictionary consisting of a single key:

 `{'question': ['What was the amount of revenue in the quarter?']} `  

The model has been designed to accept one of three different parameters to guide the type of question-answer created:

-- 'question' (generates a standard question)
-- 'boolean' (generates a 'yes-no' question)
-- 'multiple choice' (generates a multiple choice question)

Note: we would recommend using a higher temperature (0.5+) with sampling (True) to get a wider and more interesting variety of question generations. If you turn off sampling or use a lower temperature, then expect the questions to be more generic and repetitive, (e.g, 'What are the top points in this text?').

Note: if you are using 'multiple choice' mode, set a slightly lower temperature for best results (e.g., 0.2-0.3).

slim-q-gen-phi-3 is the Pytorch version of the model, and suitable for fine-tuning for further domain adaptation.

To pull the model via API:

from huggingface_hub import snapshot_download           
snapshot_download("llmware/slim-q-gen-phi-3-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-q-gen-phi-3-tool", temperature=0.7, sample=True)  
response = model.function_call(text_sample, params=['boolean'])  

# this one line will download the model and run a series of tests  
ModelCatalog().tool_test_run("slim-q-gen-phi-3-tool", verbose=True, temperature=0.7, sample=True)   

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

Model Card Contact

Darren Oberst & llmware team

Any questions? Join us on Discord