LiteRT-LM

Model Card for Granite-4.0-350M LiteRT-LM

Granite-4.0-350M LiteRT-LM model.

This can be run in txtai using the following code.

from txtai import LLM

llm = LLM("neuml/granite-4.0-350m-litert-lm/granite-4.0-350m.litertlm")
llm("Run a prompt here")

Created using the following code.

# pip install litert-torch

from litert_torch.generative.export_hf.export import export

export(
    model="ibm-granite/granite-4.0-350m",
    output_dir="output",
    externalize_embedder=True,
)
Downloads last month
50
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NeuML/granite-4.0-350m-litert-lm

Finetuned
(15)
this model