arxiv:2610.26770
š¤ Open to Collab
Junrulu
Junrulu
AI & ML interests
None yet
Recent Activity
repliedto their post 4 days ago
We are pleased to introduce a brand-new lightweight LLM, Youtu-LLM:
(1) Youtu-LLM has a total of 2B parameters, employing a 32-layer dense MLA architecture and equipped with an innovative STEM- and agentic-oriented vocabulary;
(2) Based on approximately 11T tokens of pre-training, particularly with native 128k long context extension and native agentic mid-training, Youtu-LLM-2B is comparable to Qwen3-4B in general and agent capabilities;
(3) We have open-sourced the Base/Instruct versions, as well as the evaluation code for reproducing the test metrics. In the technical report, we share our experience of native agentic pre-training in detail.
Youtu-LLM-2B is very suitable as a starting point for exploring on-device agent practice. Meanwhile, we are currently extending this paradigm to larger-scale explorations. We welcome more discussion and collaboration!
š Check the project here: https://github.com/TencentCloudADP/youtu-tip/tree/master/youtu-llm
š¤ Check the models here: https://huggingface.co/collections/tencent/youtu updated a model 4 days ago
tencent/Youtu-LLM-A7B-Base updated a model 4 days ago
tencent/Youtu-LLM-2BOrganizations
arxiv:2610.16354
arxiv:2608.28476
arxiv:2608.28478
arxiv:2605.25343
arxiv:2605.18451
arxiv:2601.19798
arxiv:2512.24618
arxiv:2511.20102
arxiv:2506.07570
arxiv:2504.14753
arxiv:2502.19230
arxiv:2502.11387
arxiv:2409.16913
arxiv:2408.02302
arxiv:2406.10957
arxiv:2406.06379
arxiv:2406.03866
arxiv:2402.11811
arxiv:2308.08239
arxiv:2305.04522
arxiv:2302.05574
arxiv:2210.12902
arxiv:2011.00519
