Swallow-8Bは追加の日本語継続事前学習により日本語が大変流暢なLlama-3です。
MetaのInstructionモデルとの差分ベクトルマージを行いました。

rinna/llama-3-Swallow-8b + 0.7*(meta-llama/Meta-Llama-3-8B-Instruct - meta-llama/Meta-Llama-3-8B)

詳細はLlama-3-Swallow-8bをご確認ください。

Downloads last month: 16

Safetensors

Model size

8.03B params

Tensor type

BF16

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for aixsatoshi/Llama3-Swallow-8B-instruct-vector-merged

Quantizations

1 model