From 333e4f3098005721682e5f75f418a617351ee8f7 Mon Sep 17 00:00:00 2001 From: Tai An Date: Sat, 25 Apr 2026 15:18:21 -0700 Subject: [PATCH] fix(gallery): normalize inconsistent tag casing/plurals across gallery models MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - embeddings → embedding (6 models): aligns with the WebUI filter button defined in core/http/views/models.html ({ term: 'embedding', ... }), so models like nomic-embed-text-v1.5 now appear under the Embedding filter - TTS → tts (5 models), ASR → asr (2 models): lowercase, per existing convention used by 161+ models - CPU/Cpu → cpu (17 models), GPU → gpu (17 models): lowercase, per existing convention used by 666+ models - dedupe duplicate tag entries on 3 models that already had repeated tags (gpt-oss-20b had gguf x2; arcee-ai/AFM-4.5B had gpu x2; one Qwen model had default x2) Closes #9247 --- gallery/index.yaml | 45 +++++++++++++++++++++------------------------ 1 file changed, 21 insertions(+), 24 deletions(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index 380bc83e8228..ac5b3db6ffee 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -743,7 +743,6 @@ - https://huggingface.co/mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-i1-GGUF tags: - default - - default overrides: parameters: model: llama-cpp/models/Qwen3.-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic.i1-Q4_K_M.gguf @@ -1915,7 +1914,7 @@ Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. tags: - text-to-speech - - TTS + - tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png name: "qwen3-tts-1.7b-custom-voice" @@ -1947,7 +1946,7 @@ Fish Speech S2-Pro is a high-quality text-to-speech model supporting voice cloning via reference audio. Uses a two-stage pipeline: text to semantic tokens (LLaMA-based) then semantic to audio (DAC decoder). tags: - text-to-speech - - TTS + - tts - voice-cloning license: apache-2.0 icon: https://huggingface.co/fishaudio/s2-pro/resolve/main/overview.png @@ -1966,7 +1965,7 @@ Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. tags: - speech-recognition - - ASR + - asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png name: "qwen3-asr-1.7b" @@ -2575,7 +2574,7 @@ license: mit tags: - text-to-speech - - TTS + - tts name: "vibevoice" urls: - https://github.com/microsoft/VibeVoice @@ -2609,7 +2608,7 @@ license: mit tags: - text-to-speech - - TTS + - tts name: "pocket-tts" urls: - https://github.com/kyutai-labs/pocket-tts @@ -3057,8 +3056,8 @@ license: apache-2.0 tags: - gguf - - GPU - - CPU + - gpu + - cpu - text-to-text - jamba - mamba @@ -3082,8 +3081,8 @@ icon: https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png tags: - gguf - - GPU - - CPU + - gpu + - cpu - text-to-text urls: - https://huggingface.co/ibm-granite/granite-4.0-h-small @@ -3145,8 +3144,8 @@ license: apache-2.0 tags: - gguf - - GPU - - CPU + - gpu + - cpu - text-to-text icon: https://cdn-avatars.huggingface.co/v1/production/uploads/64f187a2cc1c03340ac30498/TYYUxK8xD1AxExFMWqbZD.png urls: @@ -3169,8 +3168,8 @@ license: mit tags: - gguf - - GPU - - CPU + - gpu + - cpu - text-to-text icon: https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/9Bnn2AnIjfQFWBGkhDNmI.png name: "aurore-reveil_koto-small-7b-it" @@ -3197,8 +3196,8 @@ tags: - multimodal - gguf - - GPU - - Cpu + - gpu + - cpu - image-to-text - text-to-text description: | @@ -3819,7 +3818,6 @@ - gguf - gpu - cpu - - gguf - openai icon: https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-20b.svg urls: @@ -4005,7 +4003,6 @@ tags: - gguf - gpu - - gpu - text-generation description: | AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of TorchTitan for pretraining, Axolotl for supervised fine-tuning, and a modified version of Verifiers for reinforcement learning. @@ -9112,7 +9109,7 @@ description: | Granite-Embedding-107M-Multilingual is a 107M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. This model is developed using contrastive finetuning, knowledge distillation and model merging for improved performance. tags: - - embeddings + - embedding overrides: backend: llama-cpp embeddings: true @@ -9130,7 +9127,7 @@ description: | Granite-Embedding-125m-English is a 125M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 768. Compared to most other open-source models, this model was only trained using open-source relevance-pair datasets with permissive, enterprise-friendly license, plus IBM collected and generated datasets. While maintaining competitive scores on academic benchmarks such as BEIR, this model also performs well on many enterprise use cases. This model is developed using retrieval oriented pretraining, contrastive finetuning and knowledge distillation. tags: - - embeddings + - embedding overrides: embeddings: true parameters: @@ -9147,7 +9144,7 @@ description: | EmbeddingGemma 300M is a lightweight, high-quality embedding model from Google, based on the Gemma architecture. It produces 1024-dimensional embeddings optimized for retrieval and semantic similarity tasks. This GGUF version uses QAT (Quantization-Aware Training) Q8_0 quantization for efficient inference. tags: - - embeddings + - embedding overrides: backend: llama-cpp embeddings: true @@ -15923,7 +15920,7 @@ tags: - gpu - cpu - - embeddings + - embedding - python name: "all-MiniLM-L6-v2" url: "github:mudler/LocalAI/gallery/sentencetransformers.yaml@master" @@ -16776,7 +16773,7 @@ description: | llama3.2 embeddings model. Using as drop-in replacement for bert-embeddings tags: - - embeddings + - embedding overrides: embeddings: true parameters: @@ -18499,7 +18496,7 @@ description: | Resizable Production Embeddings with Matryoshka Representation Learning tags: - - embeddings + - embedding overrides: embeddings: true parameters: