wasmer-java VS LLM-Finetuning-Hub

Great idea! Luckily, there's https://github.com/wasmerio/wasmer-java, so you can easily run that wasm binary in your JVM running in your browser!

The biggest integration library is wasmer. It's intended as a server runtime for wasm. The official port wasmer-java has the problem of not supporting imports and that's also not to be implemented in the near future (they are restructuring the wasmer library according to this issue), the other is wasmer-jni. An inofficial jni-binding for the wasmer base implementation. Less nice to use, but feature complete.

Check how the rust compiler can target Web Assembly and then have a look at https://github.com/wasmerio/wasmer-java

If your savvy with WASM I think you could compile to wasm and make java bindings with https://github.com/wasmerio/wasmer-java

Hi everyone, we've been working on benchmarking different open-source LLMs. We measure, in particular, on the performance of these models once finetued (via QLoRA) on classic NLP downstream tasks like summarization and classification. We also put particular emphasis on benchmarking inference time/cost for these models once deployed.

Hello all,

I have been working on benchmarking different LLMs -- both open-source and closed-source.

Repo: https://github.com/georgian-io/LLM-Finetuning-Hub

Precisely, I am comparing their out-of-the-box capabilities (prompting) and their fine-tuned conterparts!

So far, the following models have been benchmarked:

Open-Source:

- Finetuning with QLoRA

I evaluate how Falcon does on classification tasks when compared to Bert and Distilbert.

Moreover, I talk about different ways you can deploy the model, and the associated costs!

The code for all of my experiments are available on: https://github.com/georgian-io/LLM-Finetuning-Hub

Happy reading and learning!