transformers-js icon indicating copy to clipboard operation
transformers-js copied to clipboard

Browser-compatible JS library for running language models

Results 7 transformers-js issues
Sort by recently updated
recently updated
newest added

Hi. When i try to convert the T5 small as mentioned on the readme to onnx format, I get the below error export_and_get_onnx_model() got an unexpected keyword argument 'custom_output_path'

Hi, Is the implementation of tokenizer the same as Google's SentencePiece? For example, will the same input have the same output when calling encode? If so, how can I convert...

I have this code ```js import { pipeline } from "https://cdn.jsdelivr.net/npm/@xenova/[email protected]"; let storyTeller = await pipeline( "text2text-generation", ); async function story() { let result = await storyTeller("give a story on...

Assumed the tokenizer is the quite the same, is [flan t5](https://huggingface.co/google/flan-t5-base) supported?

First of all, let me start by complimenting your amazing work. I am trying to learn AI/ML for the job market. Transformer models seem to be the state-of-the-art AI models,...

question

Thanks. feasible to train our own data?

To simply your implementation, might be better to use the tokenizers through WASM https://blog.mithrilsecurity.io/porting-tokenizers-to-wasm/