Franchuk Petro

Hi, I've similar issue while quantazing Falcon1B model: `TypeError: FalconDecoderLayer.forward() missing 1 required positional argument: 'alibi'` Here is my code: ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer model_path...

Same problem for me with VertexAI stack in jupyter notebook. Slightly different models and embeddings used, but I'm getting this error right from the start of test set generation process.

@abetatos UPD I've take a look into [this PR](https://github.com/explodinggradients/ragas/pull/689), as a result of[ issue you've mentioned here](https://github.com/explodinggradients/ragas/issues/681). I tried to clone that dev branch with fix, and install ragas from...

@ialexivy I have same misunderstanding, have you figured out list of supported languages? I assume that if there is no language-specific phoneme ASR Model for the specified language, this step...

Would appreciate if I can get any help here. This issues significantly impacts the whole idea behind OpenAI Responses API and agentic workflows overall.