RichardErkhov
/

timpal0l_-_mini-llama-awq

4-bit precision

Model card Files Files and versions Community

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Quantization made by Richard Erkhov.

Request more models

mini-llama - AWQ

Model creator: https://huggingface.co/timpal0l/
Original model: https://huggingface.co/timpal0l/mini-llama/

Original model description:

license: apache-2.0

Small random initialized llama

gpt-sw3 tokenizer

Downloads last month: 4

Safetensors

Model size

347M params

Tensor type

I32

·

FP16

·

Inference API

Unable to determine this model's library. Check the docs .