Satheesh Kola

hi @LiGuo12 , could you please provide the link for pre trained weights?

> ### 标题：SSH 连接服务器运行时无法进行可视化仿真 > > **问题描述:** > > 我通过 SSH 连接到一台 Linux 服务器运行 `genesis` 库的代码。这台服务器是 headless 的，没有图形显示设备。当我尝试使用 `gs.Scene(show_viewer=True)` 初始化场景时，程序抛出错误，提示 “No display detected. Use `show_viewer=False` for headless mode.”。这导致我无法在 SSH 连接的情况下直接进行可视化仿真。...

> Yes, we did not expand the medical-related data; both the pre-training and SFT stages remain exactly the same as in InternVL2.5. Thanks for this information @Lechatelia

please include the code for end to end fine tuning / pre training for audio lanugage models into your existing pipeline.If possible please integrate the moshi audio language model also...

@theomonnom @longcw The failing test `test_chat_ctx.py::test_summarize` appears to be unrelated to my changes. My changes: - Only modified Anthropic plugin files (`llm.py` and `utils.py`) - All 71 other tests pass...

### Usage Use **Azure Anthropic** inside an `AgentSession`: ```python from livekit.plugins import anthropic session = AgentSession( llm=anthropic.LLM.with_azure( azure_deployment="", # e.g. claude-opus-4-5 azure_endpoint="https://.services.ai.azure.com/anthropic/", api_key="", api_version="2023-06-01", ), # ... tts, stt, vad,...