Модель на базе llama-3.1-8B с датасетом от знаменитой Сайги.

Uploaded model

Эта Meta-Llama-3.1-8B модель тренирована в 2 раза быстрей с помощью Unsloth и TRL библиотеки Huggingface

Safetensors

Model size

8.03B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for burgasdotpro/Sebushka-llama-3.1-8B

Base model

Quantized

Finetuned

(621)

this model

Merges

Quantizations