Farook (EDev) Al-Sammarraie
Farook (EDev) Al-Sammarraie
This PR adds a new element (BenchmarkSet) which bundles together benchmarks that are mostly similar but need to be run separately (i.e. different models or datasets but same function). Under...
Things left to do on this dataset are as follows: - [x] Finish code to convert data to `.tfrecord` - [x] Finish code to handle sending and receiving data. -...
This issue relates to the LLM Pipeline and related backend/driver changes. Current Implementation Information*: - Pipeline is able to initialize the model and interpreter, allocate tensors, set up KV caches....
with multiple models such as 1b, 3b, or 8b (and possibly multiple datasets such as mmlu or ifeval)
This issue is a general container for matters relating to datasets in general. Discussions on TinyMMLU or IFEval specifically should go in the sub issues for this one. ## Current...
As described in the parent issue, implementation of TinyMMLU is quite complete. The only things I think might need to be done are: - ~Load data sample by sample as...
This is the main issue for discussions and information regarding the process of converting Llama models to `.tflite` format using Ai-Edge-Torch. Current Status: - [x] Llama 3.2 1B: Native Support*,...
Closes #1032
Once resources are downloaded, checksum validation holds up the process for at least 1 or 2 minutes, this is also true when no resources actually need to be downloaded. (Tested...
The [Wakelock plugin](https://pub.dev/packages/wakelock) has been discontinued and superseded by [wakelock-plus](https://pub.dev/packages/wakelock_plus). [Migration](https://github.com/fluttercommunity/wakelock_plus?tab=readme-ov-file#migrating-from-the-wakelock-plugin) is required.