全站搜索
AI 模型 84767
- Phi_3.5_mini_GGUF↗
codegood
- Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF↗
cognitivetech
- bge-m3-es-legal-tmp-6↗
dariolopez
- void.1↗
dotlabs
> - 🔹 best under 90m on sub-100m on open slm leaderboard! > - 🔸 void.2 paused to train better models focusing on stronger performance and usability. > - ▫️ step 900,000 updated with better performance, lr decayed to zero on ~10b additional bytes. State of the art, small language model pretrained from scratch on a diverse set of high-quality texts and an internal symbolic kernel. This is the first step into a series of models designed for fine-grained understanding of abstract/symbolic reasoning on text while being grounded on english. void.1 (24.38 II) achieves similar and often higher performance than palmer-006 (23.33 II) across all benchmarks and sets a new standard for future models.
- hubert_dummy↗
espnet
- fasttext-diq-vectors↗
facebook
- mms-300m↗
facebook
MMS is Facebook AI's massive multilingual pretrained model for speech ("MMS"). It is pretrained in with Wav2Vec2's self-supervised training objective on about 500,000 hours of speech data in over 1,400 languages. **Note**: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out the **How-to-fine section or **this blog** for more information about ASR. - How to Finetune - Model details - Additional links
- mms-tts-stp↗
facebook
- drama-3-int4↗
fishaudio
**The smallest working Drama 3.** Unofficial int4 quantization of fishaudio/drama-3 — Fish Audio's 35B (3B active) multi-speaker TTS model — with **real eval numbers** and one-command serving through SGLang Omni. The two checkpoints were compared on one H200 with the default SGLang Omni server settings: the 1,088 Seed-TTS English prompts, each cloning the voice of its own reference clip, sent as non-streaming requests at concurrency 8. WER is computed on the generated audio transcribed by Qwen3-ASR-1.7B. The int4 checkpoint is about 8% slower per request and its WER stays at the FP8 level: the gap between the two is about as large as the run-to-run spread of one checkpoint (a second FP8 run measured 1.365 s mean latency and 2.02% WER).
- multiberts-seed_24↗
Google
