RichardErkhov
/

chargoddard_-_SmolLlamix-8x101M-take2-4bits

Text Generation

text-generation-inference

Inference Endpoints

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

SmolLlamix-8x101M-take2 - bnb 4bits

Model creator: https://huggingface.co/chargoddard/
Original model: https://huggingface.co/chargoddard/SmolLlamix-8x101M-take2/

Original model description:

license: apache-2.0 datasets: - togethercomputer/RedPajama-Data-1T-Sample language: - en

This is another training run of SmolLlamix-8x101M with slightly different hyperparameters. Just testing to see how it holds up against the first run.

Downloads last month: 76

Safetensors

Model size

229M params

Tensor type

F32

·

FP16

·

U8

·

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported Inference Providers.