From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence
Paper
•
2511.18538
•
Published
•
187
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Soft Adaptive Policy Optimization
terryyz
authored
a
paper
about 13 hours ago
chujiezheng
authored
2
papers
about 21 hours ago
danielhanchen
posted
an
update
4 days ago
Post
8012
Qwen3-Next can now be Run locally! (30GB RAM)
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
💜 Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
💜 Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
littlebird13
updated
a
Space
5 days ago
littlebird13
published
a
Space
5 days ago
littlebird13
updated
a
Space
5 days ago
danielhanchen
posted
an
update
25 days ago
Post
4095
You can now run Kimi K2 Thinking locally with our Dynamic 1-bit GGUFs:
unsloth/Kimi-K2-Thinking-GGUF
We shrank the 1T model to 245GB (-62%) & retained ~85% of accuracy on Aider Polyglot. Run on >247GB RAM for fast inference.
We also collaborated with the Moonshot AI Kimi team on a system prompt fix! 🥰
Guide + fix details: https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally
We shrank the 1T model to 245GB (-62%) & retained ~85% of accuracy on Aider Polyglot. Run on >247GB RAM for fast inference.
We also collaborated with the Moonshot AI Kimi team on a system prompt fix! 🥰
Guide + fix details: https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally
SivilTaram
authored
a
paper
26 days ago
hzhwcmhf
updated
6
models
26 days ago
Qwen/Qwen3Guard-Gen-8B
Text Generation
•
8B
•
Updated
•
20k
•
77
Qwen/Qwen3Guard-Gen-0.6B
Text Generation
•
0.8B
•
Updated
•
89k
•
47
Qwen/Qwen3Guard-Gen-4B
Text Generation
•
4B
•
Updated
•
8.98k
•
30
Qwen/Qwen3Guard-Stream-0.6B
Feature Extraction
•
0.6B
•
Updated
•
16.6k
•
21
Qwen/Qwen3Guard-Stream-8B
Feature Extraction
•
8B
•
Updated
•
603
•
30
Qwen/Qwen3Guard-Stream-4B
Feature Extraction
•
4B
•
Updated
•
398
•
17
Post
3157
Kimi K2 Thinking is now live on the hub 🔥
moonshotai/Kimi-K2-Thinking
✨ 1T MoE for deep reasoning & tool use
✨ Native INT4 quantization = 2× faster inference
✨ 256K context window
✨ Modified MIT license
moonshotai/Kimi-K2-Thinking
✨ 1T MoE for deep reasoning & tool use
✨ Native INT4 quantization = 2× faster inference
✨ 256K context window
✨ Modified MIT license
jinjieni
authored
2
papers
27 days ago
xianbao
authored
a
paper
28 days ago
Post
610
Chinese open source AI in October wasn’t about bigger models, it was about real world impact 🔥
https://huggingface.co/collections/zh-ai-community/october-2025-china-open-source-highlights
✨ Vision-Language & OCR wave 🌊
- DeepSeek-OCR : 3B
- PaddleOCR-VL : 0.9B
- Qwen3-VL : 2B / 4B / 8B / 32B /30B-A3B
- Open-Bee: Bee-8B-RL
- http://Z.ai Glyph :10B
OCR is industrializing, the real game now is understanding the (long context) document, not just reading it.
✨ Text generation: scale or innovation?
- MiniMax-M2: 229B
- Antgroup Ling-1T & Ring-1T
- Moonshot Kimi-Linear : linear-attention challenger
- Kwaipilot KAT-Dev
Efficiency is the key.
✨ Any-to-Any & World-Model : one step forward to the real world
- BAAI Emu 3.5
- Antgroup Ming-flash-omni
- HunyuanWorld-Mirror: 3D
Aligning with the “world model” globally
✨ Audio & Speech + Video & Visual: released from entertainment labs to delivery platforms
- SoulX-Podcast TTS
- LongCat-Audio-Codec & LongCat-Video by Meituan delivery paltform
- xiabs DreamOmni 2
Looking forward to what's next 🚀
https://huggingface.co/collections/zh-ai-community/october-2025-china-open-source-highlights
✨ Vision-Language & OCR wave 🌊
- DeepSeek-OCR : 3B
- PaddleOCR-VL : 0.9B
- Qwen3-VL : 2B / 4B / 8B / 32B /30B-A3B
- Open-Bee: Bee-8B-RL
- http://Z.ai Glyph :10B
OCR is industrializing, the real game now is understanding the (long context) document, not just reading it.
✨ Text generation: scale or innovation?
- MiniMax-M2: 229B
- Antgroup Ling-1T & Ring-1T
- Moonshot Kimi-Linear : linear-attention challenger
- Kwaipilot KAT-Dev
Efficiency is the key.
✨ Any-to-Any & World-Model : one step forward to the real world
- BAAI Emu 3.5
- Antgroup Ming-flash-omni
- HunyuanWorld-Mirror: 3D
Aligning with the “world model” globally
✨ Audio & Speech + Video & Visual: released from entertainment labs to delivery platforms
- SoulX-Podcast TTS
- LongCat-Audio-Codec & LongCat-Video by Meituan delivery paltform
- xiabs DreamOmni 2
Looking forward to what's next 🚀