Lei Chen

Just tested on Python 2.7 and met the same issue if using more than one GPU.

another solution could be adding `super().__init__(model=model)` in your `__init__` since `LM` base class already has a default `kwargs` inside. https://github.com/stanfordnlp/dspy/blob/4c6a2ffb6e9dd64dd6e5a587b468c695487f9136/dsp/modules/lm.py#L8

I am also testing OPT 6.7B model on its FP16 version and smoothquant version provided by Han's lab. First, met the following warning and later model accuracy is 0.0 `Some...

When including floatX=float32 in the THEANO_FLAGS, I met the same issue. However, without specifying floatX, the code works on my Mac Book Pro. However, Yoon's code doesn't print out running...

@haileyschoelkopf , regarding your proposal `My preference would be to support multi-node via, say, allowing for multiple self-hosted API inference servers with data-parallel vLLM`, do you mind referring some implementations...

Did more reading on why [6+1] was used. Inside `mgsm/utils.py`, we can find ```python "en": { # English "QUESTION": "Question:", "ANSWER": "Step-by-Step Answer:", "DIRECT": "Answer:", "REGEX": "The answer is (\\-?[0-9\\.\\,]+)",...

Made a PR to fix the issues we observed above. Now generated contexts look normal. For example, for `mgsm_direct_en`, new yaml file will be ```yaml !!@@##@@!! -- Example 1 Question:...