From 4e0631f7c3298443f473e4eecb241fb21da8e8af Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Thu, 10 Sep 2026 15:42:10 +0000 Subject: [PATCH] Link North Small Translate W4A16 weights --- fern/pages/models/north/north-small-translate-1.0.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fern/pages/models/north/north-small-translate-1.0.mdx b/fern/pages/models/north/north-small-translate-1.0.mdx index 2ee40c94..94cbf5e0 100644 --- a/fern/pages/models/north/north-small-translate-1.0.mdx +++ b/fern/pages/models/north/north-small-translate-1.0.mdx @@ -38,7 +38,7 @@ import { ModelShowcase, Capability, Endpoint} from "../../../components/model-sh North Small Translate is an open-weights mixture-of-experts (MoE) model purpose-built for machine translation. It has 218 billion total parameters, with 25 billion active parameters, and a 16K context length. -The model provides flexible deployment options for research and enterprise use. Its FP8 weights are available +The model provides flexible deployment options for research and enterprise use. Its NVFP4 W4A16 weights are available under the [Creative Commons Attribution-NonCommercial 4.0 license](https://creativecommons.org/licenses/by-nc/4.0/) for non-commercial use. Enterprises can purchase a commercial license and deploy the model through [Model Vault](../../v2/docs/model-vault). @@ -176,7 +176,7 @@ print(response.message.content[0].text) - **Cohere API**: Try the model on the free tier through the Chat V2 API. - **Open weights**: Download the - [FP8 model from Hugging Face](https://huggingface.co/CohereLabs/North-Small-Translate-1.0-fp8) for + [NVFP4 W4A16 model from Hugging Face](https://huggingface.co/CohereLabs/North-Small-Translate-1.0-w4a16) for non-commercial use under the CC BY-NC 4.0 license. - **Commercial deployment**: Use a commercially licensed deployment through [Model Vault](../../v2/docs/model-vault). The suggested hardware is two H100 GPUs or one B200 GPU.