Çağatay Çallı

v1.1 is more appropriate for almost anything. `get_orderbook` also reports inconsistent results in v2.0

@skyl @tanner314 `get_orderbook` also returns something totally different at times. You'll notice in subsequent calls. It happens like %20 of the time.

> You can easily fix this by adding the large text2img to the params: > > ```shell > python scripts/txt2img.py \ > --prompt "a virus monster is playing guitar, oil...

@talatccan `disambiguate` expects its input from sys.stdin. When you see tensorflow waiting, it's time to write a sentence and hit Enter.

MPS utilization is possible upon the release of this PR for pytorch, you could try with a custom build with that branch: https://github.com/pytorch/pytorch/pull/99272

@soxziw I'm running this in Google Colab and I got the exact same failure when running run_tests.sh ``` FAIL: test_lm_score_may_fail_numerically_for_external_meliad (__main__.LmInferenceTest) ---------------------------------------------------------------------- Traceback (most recent call last): File "/content/alphageometry/lm_inference_test.py", line...

There is slight problem with initialization of context length value in Chat Settings UI for models providing such long context support. When you adjust by hand through this UI, it...

I think @mckaywrigley didn't want to blindly max out the context length setting to not incur unpredictable costs on user's end.

You can mitigate this for your existing Supabase messages table by executing: `ALTER TABLE messages ADD assistant_id uuid` through your Supabase client dashboard: http://localhost:54323/project/default/sql/1 Note that the problem happens at...

amiradib, why do you think that line is incorrect? With that line, we keep a buffer of (article id, article title) tuples and if the buffer fills up, write them...