|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# SLIM-Q-GEN-TINY-TOOL |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
|
|
|
**slim-q-gen-tiny-tool** is a 4_K_M quantized GGUF version of slim-q-gen-tiny, 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 one 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), and 'multiple choice' (generates a multiple choice question). |
|
|
|
|
|
slim-qa-gen-tiny-tool is a fine-tune of a tinyllama (1b) parameter model, designed for fast, local deployment and rapid testing and prototyping. Please also see slim-q-gen-phi-3-tool, which is finetune of phi-3, and will provide higher-quality results, at the trade-off of slightly slower performance and requiring more memory. |
|
|
|
|
|
|
|
|
[**slim-q-gen-tiny**](https://huggingface.co/llmware/slim-q-gen-tiny) 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-tiny-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-tiny-tool", sample=True, temperature=0.7) |
|
|
response = model.function_call(text_sample, params=['question']) |
|
|
|
|
|
# this one line will download the model and run a series of tests |
|
|
ModelCatalog().tool_test_run("slim-q-gen-tiny-tool", verbose=True) |
|
|
|
|
|
|
|
|
Note: please review [**config.json**](https://huggingface.co/llmware/slim-q-gen-tiny-tool/blob/main/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](https://discord.gg/MhZn5Nc39h) |
