Post
1910
Where gone streamlit in huggingface?
- 2 replies
Chinese LLMs on Hugging Face
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
zh-ai-community's activity
AdinaY
updated
a
collection
3 days ago
Ningyu
authored
7
papers
3 days ago
BiasEdit: Debiasing Stereotyped Language Models via Model Editing
Paper
•
2503.08588
•
Published
•
7
LookAhead Tuning: Safer Language Models via Partial Answer Previews
Paper
•
2503.19041
•
Published
•
5
ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
Paper
•
2503.21088
•
Published
•
7
Agentic Knowledgeable Self-awareness
Paper
•
2504.03553
•
Published
•
28
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
Paper
•
2504.03561
•
Published
•
18
Conceptualized Representation Learning for Chinese Biomedical Text Mining
Paper
•
2008.10813
•
Published
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Paper
•
2505.14681
•
Published
•
9
AdinaY
updated
a
collection
3 days ago
Post
2580
ByteDance is absolutely cooking lately🔥
BAGEL 🥯 7B active parameter open multimodal foundation model by Bytedance Seed team.
ByteDance-Seed/BAGEL-7B-MoT
✨ Apache 2.0
✨ Outperforms top VLMs (Qwen2.5-VL & InternVL-2.5)
✨ Mixture-of-Transformer-Experts + dual encoders
✨ Trained on trillions of interleaved tokens
BAGEL 🥯 7B active parameter open multimodal foundation model by Bytedance Seed team.
ByteDance-Seed/BAGEL-7B-MoT
✨ Apache 2.0
✨ Outperforms top VLMs (Qwen2.5-VL & InternVL-2.5)
✨ Mixture-of-Transformer-Experts + dual encoders
✨ Trained on trillions of interleaved tokens
AdinaY
updated
a
collection
3 days ago
AdinaY
updated
a
collection
4 days ago
Post
2310
Dolphin 🔥 A multimodal document image parsing model from ByteDance
, built on an analyze-then-parse paradigm.
ByteDance/Dolphin
✨ MIT licensed
✨ Handles text, tables, figures & formulas via:
- Reading-order layout analysis
- Parallel parsing with smart prompts
, built on an analyze-then-parse paradigm.
ByteDance/Dolphin
✨ MIT licensed
✨ Handles text, tables, figures & formulas via:
- Reading-order layout analysis
- Parallel parsing with smart prompts
AdinaY
updated
a
collection
4 days ago
AdinaY
updated
a
collection
5 days ago
Post
516
Index-AniSora 🎬 an open anime video model released by Bilibili
👉https://huggingface.co/IndexTeam/Index-anisora
✨ Apache2.0
✨ Supports many 2D styles: anime, manga, VTubers, and more
✨ Fine control over characters and actions with smart masking
👉https://huggingface.co/IndexTeam/Index-anisora
✨ Apache2.0
✨ Supports many 2D styles: anime, manga, VTubers, and more
✨ Fine control over characters and actions with smart masking
AdinaY
updated
a
collection
5 days ago
Post
1806
Data quality is the new frontier for LLM performance.
Ultra-FineWeb 📊 a high-quality bilingual dataset released by OpenBMB
openbmb/Ultra-FineWeb
✨ MIT License
✨ 1T English + 120B Chinese tokens
✨ Efficient model-driven filtering
Ultra-FineWeb 📊 a high-quality bilingual dataset released by OpenBMB
openbmb/Ultra-FineWeb
✨ MIT License
✨ 1T English + 120B Chinese tokens
✨ Efficient model-driven filtering
-
- 2 replies
AdinaY
updated
a
collection
6 days ago