From 12c8b52b5ed013ab4ad594164e23d5fa68e2ba26 Mon Sep 17 00:00:00 2001 From: davidmezzetti <561939+davidmezzetti@users.noreply.github.com> Date: Tue, 14 Apr 2026 10:12:05 -0400 Subject: [PATCH] Update recommended models and links --- README.md | 9 ++++----- docs/models.md | 9 ++++----- 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index a97f2a96..b0d0aa78 100644 --- a/README.md +++ b/README.md @@ -204,9 +204,9 @@ See the table below for the current recommended models. These models all allow c | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------ | | [Embeddings](https://neuml.github.io/txtai/embeddings) | [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | | [Image Captions](https://neuml.github.io/txtai/pipeline/image/caption) | [BLIP](https://hf.co/Salesforce/blip-image-captioning-base) | -| [Labels - Zero Shot](https://neuml.github.io/txtai/pipeline/text/labels) | [BART-Large-MNLI](https://hf.co/facebook/bart-large) | +| [Labels - Zero Shot](https://neuml.github.io/txtai/pipeline/text/labels) | [DeBERTa v3 Zeroshot](https://hf.co/MoritzLaurer/deberta-v3-base-zeroshot-v2.0-c) | | [Labels - Fixed](https://neuml.github.io/txtai/pipeline/text/labels) | Fine-tune with [training pipeline](https://neuml.github.io/txtai/pipeline/train/trainer) | -| [Large Language Model (LLM)](https://neuml.github.io/txtai/pipeline/text/llm) | [gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) | +| [Large Language Model (LLM)](https://neuml.github.io/txtai/pipeline/text/llm) | [Gemma 4 31B](https://hf.co/google/gemma-4-31B) | | [Summarization](https://neuml.github.io/txtai/pipeline/text/summary) | [DistilBART](https://hf.co/sshleifer/distilbart-cnn-12-6) | | [Text-to-Speech](https://neuml.github.io/txtai/pipeline/audio/texttospeech) | [ESPnet JETS](https://hf.co/NeuML/ljspeech-jets-onnx) | | [Transcription](https://neuml.github.io/txtai/pipeline/audio/transcription) | [Whisper](https://hf.co/openai/whisper-base) | @@ -218,9 +218,8 @@ See the following links to learn more. - [Hugging Face Tasks](https://hf.co/tasks) - [Hugging Face Model Hub](https://hf.co/models) -- [MTEB Leaderboard](https://hf.co/spaces/mteb/leaderboard) -- [LMSYS LLM Leaderboard](https://chat.lmsys.org/?leaderboard) -- [Open LLM Leaderboard](https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard) +- [Embeddings Leaderboard](https://hf.co/spaces/mteb/leaderboard) +- [LLM Leaderboard](https://hf.co/spaces/lmarena-ai/arena-leaderboard) ## Powered by txtai diff --git a/docs/models.md b/docs/models.md index da2e37c5..66eeeca6 100644 --- a/docs/models.md +++ b/docs/models.md @@ -8,9 +8,9 @@ See the table below for the current recommended models. These models all allow c | ---------------------------------------------------- | ------------------------------------------------------------------------ | | [Embeddings](../embeddings) | [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | | [Image Captions](./pipeline/image/caption.md) | [BLIP](https://hf.co/Salesforce/blip-image-captioning-base) | -| [Labels - Zero Shot](./pipeline/text/labels.md) | [BART-Large-MNLI](https://hf.co/facebook/bart-large) | +| [Labels - Zero Shot](./pipeline/text/labels.md) | [DeBERTa v3 Zeroshot](https://hf.co/MoritzLaurer/deberta-v3-base-zeroshot-v2.0-c) | | [Labels - Fixed](./pipeline/text/labels.md) | Fine-tune with [training pipeline](./pipeline/train/trainer.md) | -| [Large Language Model (LLM)](./pipeline/text/llm.md) | [gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) | +| [Large Language Model (LLM)](./pipeline/text/llm.md) | [Gemma 4 31B](https://hf.co/google/gemma-4-31B) | | [Summarization](./pipeline/text/summary.md) | [DistilBART](https://hf.co/sshleifer/distilbart-cnn-12-6) | | [Text-to-Speech](./pipeline/audio/texttospeech.md) | [ESPnet JETS](https://hf.co/NeuML/ljspeech-jets-onnx) | | [Transcription](./pipeline/audio/transcription.md) | [Whisper](https://hf.co/openai/whisper-base) | @@ -22,6 +22,5 @@ See the following links to learn more. - [Hugging Face Tasks](https://hf.co/tasks) - [Hugging Face Model Hub](https://hf.co/models) -- [MTEB Leaderboard](https://hf.co/spaces/mteb/leaderboard) -- [LMSYS LLM Leaderboard](https://chat.lmsys.org/?leaderboard) -- [Open LLM Leaderboard](https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard) +- [Embeddings Leaderboard](https://hf.co/spaces/mteb/leaderboard) +- [LLM Leaderboard](https://hf.co/spaces/lmarena-ai/arena-leaderboard)