kwanUm

Following as well

Joining the question.. The project seems to give really nice gains in terms of performance, and I'm trying to use it at an inference pipeline I've created. I don't seem...

Thank you for the reply. In my case, unlike in training, I'm receiving and processing the incoming audio in real-time. I'm processing about 1000 samples of audio data as they...

Traceback (most recent call last): File "/private/home/orik/.oh-my-zsh/custom/plugins/zsh_codex/create_completion.py", line 64, in response = openai.Completion.create(engine='code-davinci-002', prompt=prompt_prefix, suffix=prompt_suffix, temperature=0.5, max_tokens=50, stream=STREAM) File "/private/home/orik/.conda/envs/design5_py38/lib/python3.8/site-packages/openai/api_resources/completion.py", line 31, in create return super().create(*args, **kwargs) File "/private/home/orik/.conda/envs/design5_py38/lib/python3.8/site-packages/openai/api_resources/abstract/engine_api_resource.py", line...

Has anyone found a pre-trained model and can share please?

@carlosejimenez would you like to review this?

Seeems like a major change removeing the validation.ipynb and engine_validation.py was done here - https://github.com/princeton-nlp/SWE-bench/pull/142/files#diff-896819df1387fcab75ada7f5df54f4af5cc2d58bae1c2e287e3e1ac5f656fa3b Not sure what script replaced it yet for producing the SWE-bench dataset (not running evaluation)