Install:

pip install deepsparse[llm]==1.7

Usage:

>>> from deepsparse import TextGeneration
>>> model = TextGeneration("nm-testing/granite-7b-lab-pruned50-quant-ds")
>>> model("Hello my name is")
TextGenerationOutput(
  created=datetime.datetime(2024, 5, 1, 17, 41, 13, 176274),
  prompts='Hello my name is',
  generations=[GeneratedText(text='Alex and I am a senior in high school. I am taking a dual credit biology class this semester and I really need help with the lab. I am having trouble with the lab on dissociation and I was hoping that you could help me. The lab requires that we set up a reaction between a strong acid and a strong base and measure the pH of the solution at various points in the reaction.\n\nHere is a summary of the lab that I was given:\n\n1', score=None, finished=True, finished_reason='max_new_tokens')],
  input_tokens=None
)
Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.