-
### Describe the bug
I'm receiving an error trying to use the `diffusers` module to run the `flux` model.
> ValueError: Cannot instantiate this tokenizer from a slow version. If it's based on sent…
-
@bobbrow Thanks for the update. I am still having issues. I now see:
[cms-client] Configuring using the "ninja" CMake generator with plattform "undefined" and toolset {}
[rollbar] Unhandle…
-
I tested and found that the duration of the output audio is always 10 seconds. How to modify the code to make the output audio duration consistent with the input audio duration
-
File "/home/alg/anaconda3/envs/evalscope/lib/python3.10/site-packages/evalscope/backend/rag_eval/__init__.py", line 1, in
from evalscope.backend.rag_eval.utils.embedding import EmbeddingModel
…
-
Would it be possible to iterate the batch with more than one model? So that you choose Model Override and instead of the script using the model currently selected in the UI, you can input, say, 5 mode…
-
Just tried the new Gemma-2 9B model with a context length of around 10K Tokens. First run works fine, second run gives me the following error:
```
File "[...]exllamav2/exllamav2/generator/base.p…
-
When i follow the example on this page:
https://docs.confident-ai.com/docs/metrics-introduction
and try to use Mistral-7B as evaluation-model, i always get this error when running the exact code …
-
my Furby is connected to my computer, yet the fluffd request generator isn't working? I have the command prompt open, and whatever I try to send doesn't go through. the only thing that showed up on th…
-
at the moment compel hard-splits prompts at 75 tokens. because self-attention does not work outside of a single 75 token chunk, this can cause degraded generation especially if a word is split in the …
-
If I understand it correctly, both SAM and SAM-HQ takes box points, input points and labels (text) as input along with the input image.
What about the input images that we don't have these informati…