ModelListadosExterno

Canary Qwen 2.5b HNPU

Prebuilt HNPU artifacts for nvidia/canary-qwen-2.5b, a public automatic speech recognition model.

Fontehuggingface.co/runanywhere/canary_qwen_2.5b_HNPU/tree/0a57e0ac902def02291285bfb1520090741cf494

TipoOtherModelo basenvidia/canary-qwen-2.5bVersãoRevision 0a57e0a

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 24,7 MB–1,54 GB
Modelo base: nvidia/canary-qwen-2.5b
Versão: vRevision 0a57e0a
Atualizado: 14 de set. de 2026
Downloads: 0
Fonte: Hugging Face

Descrição da fonte

canary qwen 2.5b HNPU

Prebuilt HNPU artifacts for nvidia/canary-qwen-2.5b, a public automatic speech recognition model.

For model behavior, license, intended use, and limitations, see the upstream model card.

Artifacts are architecture-pinned. Available artifact directories: v81/.

Fontes

1 fonte

Hugging FacePrimárioVersão 0a57e0ac902def02291285bfb1520090741cf494

huggingface.co/runanywhere/canary_qwen_2.5b_HNPU/tree/0a57e0ac902def02291285bfb1520090741cf494

Verificado 14 de set.

Artefatos de modelo

6 artefatos

v81/canary/canary_host.bin

bin · 24,7 MB · SHA-256 f9a1dbaefddb…cf75 · Hugging Face

Baixar

v81/nb6_conformer.bin

bin · 1,54 GB · SHA-256 bc40e27c9db9…0dc1 · Hugging Face

Baixar

v81/qwen3_1p7b_embed_f16.bin

bin · 594 MB · SHA-256 bccd2bc5ec32…dead · Hugging Face

Baixar

v81/qwen3_merged_decode_w8.bin

bin · 1,32 GB · SHA-256 a98b9a77196a…b85b · Hugging Face

Baixar

v81/qwen3_merged_lmhead_w8.bin

bin · 300 MB · SHA-256 c1b68530558c…268f · Hugging Face

Baixar

v81/qwen3_merged_prefill_w8.bin

bin · 1,34 GB · SHA-256 61718831ddd1…76ae · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme14 de set.huggingface.co/runanywhere/canary_qwen_2.5b_HNPU

--- license: "cc-by-4.0" tags: - "hnpu" - "hexagon" - "npu" - "asr" - "v81" base_model: "nvidia/canary-qwen-2.5b" pipeline_tag: "automatic-speech-recognition" --- # canary qwen 2.5b HNPU Prebuilt HNPU artifacts for [nvidia/canary-qwen-2.5b](https://huggingface.co/nvidia/canary-qwen-2.5b), a public automatic speech recognition model. For model behavior, license, intended use, and limitations, see the [upstream model card](https://huggingface.co/nvidia/canary-qwen-2.5b). Artifacts are architecture-pinned. Available artifact directories: `v81/`.

Note14 de set.huggingface.co/runanywhere/canary_qwen_2.5b_HNPU

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Repo runanywhere/canary_qwen_2.5b_HNPU