Run the Model

tokenizer = LlamaTokenizer.from_pretrained("alexpaul/QI-large-v1")

base_model = LlamaForCausalLM.from_pretrained(
    "alexpaul/QI-large-v1",
    load_in_8bit=True,
    device_map='auto',
)

Downloads last month: 11

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

alexpaul
/

QI-Large-v1

Datasets used to train alexpaul/QI-Large-v1

Space using alexpaul/QI-Large-v1 1