Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders
六花牡丹（Rikka Botan） PRO
RikkaBotan
AI & ML interests
Japanese independent researcher having shy and pampered personality. Twin-tail hair is a charm point. Interested in nlp. Usually using python and C.
Recent Activity
liked a model about 22 hours ago
LiquidAI/LFM3-1.7B liked a model about 22 hours ago
LiquidAI/Liquid-Codec liked a dataset about 23 hours ago
LiquidAI/structured-extractionOrganizations
A lightweight, faster and high performance embedding model by adopting Separable Dynamic Tanh normalization.
-
Stable Static Embedding Semantic Web Search and Deep Web Search
💙2Test Stable Static Embedding, a faster embedding model
-
Stable Static Embedding Semantic Web Search and Deep Web Search Ja
💙Test Stable Static Embedding, a faster embedding model in Ja
-
Stable Static Embedding Semantic Web Search, Deep Web Search Ja En
💙2Test Stable Static Embedding, a faster embedding in Ja En
-
RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en
Sentence Similarity • 15.6M • Updated • 14
Original style models
-
RikkaBotan/style_bert_vits2_english_original
Text-to-Speech • Updated • 77 • 1 -
RikkaBotan/style_bert_vits2_jp_extra_sweet_original
Text-to-Speech • Updated • 327 • 2 -
RikkaBotan/style_bert_vits2_chinese_original
Text-to-Speech • Updated • 422 • 2 -
RikkaBotan/style_bert_vits2_jp_extra_cool_original
Text-to-Speech • Updated • 245 • 5
Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders
A lightweight, faster and high performance embedding model by adopting Separable Dynamic Tanh normalization.
-
Stable Static Embedding Semantic Web Search and Deep Web Search
💙2Test Stable Static Embedding, a faster embedding model
-
Stable Static Embedding Semantic Web Search and Deep Web Search Ja
💙Test Stable Static Embedding, a faster embedding model in Ja
-
Stable Static Embedding Semantic Web Search, Deep Web Search Ja En
💙2Test Stable Static Embedding, a faster embedding in Ja En
-
RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en
Sentence Similarity • 15.6M • Updated • 14
The module called SLC2, inspired by Liquid Time-Constant Networks (LTCs) and Liquid Foundation Models (LFM2), to enable faster training and inference.
Original style models
-
RikkaBotan/style_bert_vits2_english_original
Text-to-Speech • Updated • 77 • 1 -
RikkaBotan/style_bert_vits2_jp_extra_sweet_original
Text-to-Speech • Updated • 327 • 2 -
RikkaBotan/style_bert_vits2_chinese_original
Text-to-Speech • Updated • 422 • 2 -
RikkaBotan/style_bert_vits2_jp_extra_cool_original
Text-to-Speech • Updated • 245 • 5