全站搜索

AI 模型 84999

• chinese-babylm-2026-v3↗

  exusiaiw

  A compact DeBERTaV2 masked language model pretrained from scratch on Chinese child-directed and child-produced text. Designed for data-constrained language modeling with a pure-Chinese WordPiece tokenizer. Key findings: - Tokenizer granularity is the primary factor for HANZI track performance (8K vocab >> 32K vocab) - DeBERTaV2 achieves the highest NLU scores (zhoblimp: 69.89) - Radical embedding hurts performance with character-level tokenization

• wav2vec2-large-romance-voxpopuli-v2↗

  facebook

• Luna-Protocol-1.5B-Discord-Dialogues-200k-base-v2↗

  fox3000foxy

• multiberts-seed_2-step_200k↗

  Google

• multiberts-seed_3-step_1500k↗

  Google

• t5-efficient-small-el2↗

  Google

• t5gemma-ml-ml-prefixlm-it↗

  Google

• opus-mt-tc-bible-big-zhx-en↗

  Helsinki-NLP

• Embodied-R1.5↗

  IffYuan

• gemma-4-26B-A4B-it-int4-mixed-AutoRound↗

  Intel