ModelAufgelistetExtern

Qwen35 9b Omni Kaggle Build

Qwen3.5-9B native multimodal + Whisper audio branch + Jinja thinking template.

Quellehuggingface.co/Hellohihihih/qwen35-9b-omni-kaggle-build/tree/011a46256568cdc29e09e49377d7dd6206985f43

ArtOtherBasismodellQwen/Qwen3.5-9BVersionRevision 011a462CBewertung

Modellquelle

Art: Other
Dateigröße: 23,1 MB
Basismodell: Qwen/Qwen3.5-9B
Version: vRevision 011a462
Aktualisiert: 17. Okt. 2026
Downloads: 0
Quelle: Hugging Face

Quellenbeschreibung

Qwen35 Omni Kaggle Build

Qwen3.5-9B native multimodal + Whisper audio branch + Jinja thinking template.

Runtime safety:

greedy decode for audio branch
audio/text embeddings use nan_to_num + clamp before generation

Stock LM Studio requires llama.cpp qwen35_omni backend support for the custom audio branch.

Quellen

1 Quelle

Hugging FacePrimärVersion 011a46256568cdc29e09e49377d7dd6206985f43

huggingface.co/Hellohihihih/qwen35-9b-omni-kaggle-build/tree/011a46256568cdc29e09e49377d7dd6206985f43

Verifiziert 17. Aug.

Modellartefakte

1 Artefakt

audio_projector.safetensors

safetensors · 23,1 MB · SHA-256 899b7b40414b…16b2 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme17. Aug.huggingface.co/Hellohihihih/qwen35-9b-omni-kaggle-build

--- library_name: transformers base_model: - Qwen/Qwen3.5-9B tags: - qwen3.5 - omni - audio - video - image - korean - english - thinking pipeline_tag: any-to-any --- # Qwen35 Omni Kaggle Build Qwen3.5-9B native multimodal + Whisper audio branch + Jinja thinking template. Runtime safety: - greedy decode for audio branch - audio/text embeddings use nan_to_num + clamp before generation Stock LM Studio requires llama.cpp qwen35_omni backend support for the custom audio branch.

Note17. Aug.huggingface.co/Hellohihihih/qwen35-9b-omni-kaggle-build

Source context: 0 downloads · 1 likes · Pipeline any-to-any · Library transformers · Repo Hellohihihih/qwen35-9b-omni-kaggle-build