Alisamar Husain

Neural Filter sample

3

Closes: #23 

Summary of Changes - Added more information to the `LLMResult` returned by `OpenAI` - Return info in callback handler - More detailed token usage in `OpenAICallbackHandler` Fixes: #1337 Related: #873...

The LLM discards a lot of information while returning the `LLMResult` and only returns a few keys. Especially in the case of the `OpenAI` LLM, only the total token usage...

Created a Server example

13

I've created an example which provides an HTTP interface to LLaMA using [Crow](https://github.com/CrowCpp/Crow). This comes as a single header file which I've committed. Also, this library depends on Boost, so...

Using `inputs_embeds` for generation creates different results (and gives a warning)

1

I'm trying to use the `inputs_embeds` parameter to run the LLaMA model. This is part of my code. ```python # INPUT = ...embedding of a sequence, ensuring that there are...

Speed on `Device::Mps` is much slower than `Device::Cpu` on Apple M1

6

I wrote a test to see how fast a simple model can run on Apple M1 chips, using `tch`. The actual model, called `SanityModel`, is just a simple 4 layer...

Switch to better stylesheets using Sass/SCSS or modules

3

2.0 milestone

Split components into "pages" and "components"

3

2.0 milestone [Refactoring]

Prevent application crashes with error boundaries

9

2.0 Milestone https://reactjs.org/docs/error-boundaries.html

Set up tests for build and basic functionality

5

Tests can be set up with Github Actions to test the following - Is the `yarn build` successful? - Is the linting passing without errors? - Is the Docker build...