cinjon
cinjon
The default in utils/encode.py is 5.0 https://github.com/descriptinc/descript-audio-codec/blob/c7cfc5d2647e26471dc394f95846a0830e7bec34/dac/utils/encode.py#L29), while the default in model.base.py is 1.0. https://github.com/descriptinc/descript-audio-codec/blob/c7cfc5d2647e26471dc394f95846a0830e7bec34/dac/model/base.py#L129 What do you recommend actually using in inference?
Hi, I'd like to use FairSeq2 for my audio models. Is there an example of an audio data loader in the works? That would be super helpful. What I need...
When I run ` poetry run python bin/import_chain_txs.py 0x379`, I get the following error: `AttributeError: module 'OpenSSL.SSL' has no attribute 'SSLv2_METHOD'` Everything up to then was working np.
## Your Question My two types are below. I would like to return the user plus its known last latitude and longitude and nothing else. However, I am struggling to...
### ⚠️ Please check that this feature request hasn't been suggested before. - [X] I searched previous [Ideas in Discussions](https://github.com/OpenAccess-AI-Collective/axolotl/discussions/categories/ideas) didn't find any similar feature requests. - [X] I searched...
Hi, I was able to verify the MMLU score for HuggingFace gemma-2-9b-it to within .2. However, for gemma-2-27b-it, the score (52.3% on all) is way off. Is there some mistake...
I did some spot checks recently and these from the test set came are just incorrect. I didn't look very hard otherwise, but any idea what's up? Were these entered...
Hi, I'm wondering how I should be thinking of the mixed precision policies of these three packages together. My plugin is below. It works, but I don't think we're doing...