-
- do all work in a branch (rebase continually on main), the addition of big yang models will slow down compile times which is hindering development of orchestron itself
- [ ] add XR device yang model…
-
I'm trying to adapt the bitdistiller code for encoder-decoder models.
Are there any plans to add support for this? Can some guidance be provided what parts need adaptation?
We're running a proj…
-
I used the workflow on a big model with 300 runs and had to make adjustments to the snakemake workflow. I note them here for convenience.
- Change shell commands to script commands when there are m…
-
https://tybug.github.io/ossapi/serializing-models.html#serializing-models
> Please open an issue if this approach is not sufficient for your use case.
There are some cases where access to the ra…
-
Now that the models are bundled, with PR #811, the size of "node_modules/nsfwjs" is now 3 x 3 Models bigger.
The modules appear in the following subdirectories:
```
models
esm
cjs
```
The…
-
Hello!
Even though I acknowledge that a bigger share of developers could be interested in accessing instruction-tuned versions of Gemini (and that's the justified rationale behind the design choic…
-
| --- | --- |
| Bugzilla Link | [321689](https://bugs.eclipse.org/bugs/show_bug.cgi?id=321689) |
| Status | ASSIGNED |
| Importance | P5 enhancement |
| Reported | Aug 04, 2010 05:41 EDT |
| Modi…
-
`save_object` is slow for big models (~10K parameters)
## Possible improvement 1
`qs2` is a very fast format for saving and reading data. For huge models, `fit$save_object()` is slow in the `rds…
-
### Description
I'm attempting to make an API to interact with a RAG chat bot that I've made.
The API is OpenAI compatible (should be) but I cannot get big-AGI to display the response that the A…
-
is it possible to set the target device (gpu0, gpu1, cpu) per-model? that'd be a game-changer as we could offload smaller models to cpu while keeping bigger models on gpu
basically preventing the war…