-
Initial reports can be seen from https://github.com/ggerganov/llama.cpp/pull/8227
> [!IMPORTANT]
> A note for everyone: if you think there's a bug in llama.cpp tokenizer, please make sure to tes…
-
Comment below with questions or thoughts about the reading for [this week's workshop](https://github.com/uchicago-computation-workshop/Fall2019/tree/master/11-14_Terman).
Please make your comments …
-
### Your question
This is an awesome project, kuddos to you. I hope you can help me use it!
I've created a custom model for multi text classification that I've exported as an `.onnx` file (origina…
-
### Use Case
Javascript/Typescript for inflight handlers. There is currently a lot of ceremony involved in using extern as a way to consume JS/TS. When doing this, it's assumed that the user knows …
-
release date: end august (may be delayed early september waiting pytorch and numba)
wanted:
- [x] technical debt removal:
- no more NullSoft usage to create the launchers (only mkshim400.py …
-
Dataloader name: `myxnli/myxnli.py`
DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?myxnli
| Dataset| myxnli |
|-------------|---|
| Description | The myXNLI corpus is …
-
## Keyword: detection
### RacketStore: Measurements of ASO Deception in Google Play via Mobile and App Usage
- **Authors:** Authors: Nestor Hernandez, Ruben Recabarren, Bogdan Carbunar, Syed Ishti…
-
There are models available like CodeBERT and if efficient CPU inference is a target and you don't mind some quirks, bert.cpp may be an excellent GGML based inference framework.
I think this can ena…
-
It the CLI already supports calling a system using `system[Id|Address]`, `--args` and `--argTypes`. Extending that functionality, a "natural language" input with some argument parsing would significan…
-
I was playing around with the new type system and came across this issue:
```
>>> struct F { a: Current, b: Current }
>>> head([F { a: 1A, b: 2A }]).b
error: while type checking
┌─ :1:28
│
…