Liang

Implementing Streaming Output with Autogen and Chainlit Integration

6

I have a question regarding an example on https://github.com/Chainlit/cookbook/blob/main/pyautogen/app.py (or async version: https://github.com/Chainlit/cookbook/blob/main/pyautogen/async_app.py) that combines **autogen** and **chainlit**. I've been trying to modify the code to enable streaming output, but...

Authentication Failure in Copilot Mode: Missing Headers

4

I've been considering that anything related to tokens would likely utilize `header_auth_callback(headers: Dict)`. I attempted to create a mock login (which guarantees authentication success regardless of the situation) to capture...

AttributeError: 'MegatronGPTModel' object has no attribute 'decoder'

1

#### Description I am retraining a LLaMA3 model. Due to the limited size of my dataset, I attempted to use `freeze_updates` as referenced in the [NVIDIA NeMo documentation](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/core/neural_modules.html#dynamic-layer-freezing). My configuration...

I am currently using the following code to set initial actions and update the greeting message: ```python init_actions = await cl.make_async(set_init_actions)(user_knowledge=user_knowledge, chat_profile=chat_profile) greeting_msg.actions = init_actions greeting_msg.content = greeting_msg.content + "\n\nOr,...

Hello, I would like to confirm whether the current implementation supports training with both function-based reward and DPO reward simultaneously. If not, are there any planned updates or workarounds to...

No Significant Improvement Observed in Model Training Speed

8

### 🐛 Describe the bug I am training the `meta-llama/Llama-3.2-1B` model using **LLaMA-Factory** with the following YAML configuration: ```yaml ### model model_name_or_path: meta-llama/Llama-3.2-1B ### method stage: pt do_train: true do_eval:...