Gintas Z.
Gintas Z.
@Garygunn94 hey man, I'm doing something similar, but have no experience in TF yet. I have dataset of: 1. background + front audio 2. front audio (same exact audio just...
Maybe it could be a Svelte/SvelteKit app instead of React? Svelte is known to be easier to maintain than React although I am biased. Also, I see you are writing...
If I remove `max_tokens=500`, then it seems performance with regex is ~3x faster: ``` SGLang 0.1.14 | 300 batch items | 50 threads | 371.07 secs | NVIDIA H100 80GB...
This is a very much needed feature
hmm, I just wanted to try this as well... sadly not supported yet.
@hnyls2002 what would be your thoughts? I'm using SGLang for bulk information extraction, so Phi3-mini would be very interesting to try since it's only 3.8B
I've avoided the problem by replacing the YAML format for output generation with XML format. `r"\n(?:.*?\n)*```"`
Having the same error, however, I think it may be because the `auto-gpt` index is being initialised (10 minutes passed now) EDIT: index on Pinecone turned `Ready` and now `auto-gpt`...
@hnyls2002 here I was using 0.1.14 version. I know `--mem-fraction-static` should reduce these errors but my point is that if this error is thrown, then processing of other generation requests...