Francesco Cariaggi
Francesco Cariaggi
Suppose I have a pre-trained tokenizer, e.g. a `BertWordPieceTokenizer`, with its own vocabulary. My goal is to use it to tokenize some technical text which will likely contain unknown words...
I have a BERT-based sentence similarity model, namely [bert-base-nli-mean-tokens](https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens) which takes a pair and outputs a cosine similarity score which is an indication of their semantic similarity. My goal is...
[This](https://github.com/kalekiu/easyesn/blob/master/examples/PredictionExample.ipynb) sample notebook, among other things, shows how to use an ESN in generative mode, where the network, after being trained, starts being driven by its own output to generate...
Hello, Is it possible to obtain a quantized .tflite version of YOLO v3 / YOLO Tiny v3 to do INT8 inference with the tools in this repository? I've tried using...
This pull requests is an attempt towards addressing #65. Note that this is my first ever public contribution, so don't be too hard on me 😉 For `tabular-classification` and `tabular-regression`...
Expected Behavior ================= In addition to a minified Docker image, get an optimized Dockerfile that you can reuse to build new images. --- Actual Behavior ================= The minified Docker image...
### System Info - `transformers` version: 4.42.0.dev0 - Platform: Linux-5.4.0-172-generic-x86_64-with-glibc2.17 - Python version: 3.8.19 - Huggingface_hub version: 0.23.1 - Safetensors version: 0.4.3 - Accelerate version: 0.30.1 - Accelerate config: not...
As flagged in [this comment](https://github.com/huggingface/transformers/issues/31945#issuecomment-2233766500) from #31945, the [current test suite](https://github.com/huggingface/transformers/blob/72fb02c47dbbe1999ae105319f24631cad6e2e00/tests/test_modeling_common.py#L777) for gradient checkpointing may fail to spot subtle bugs. For example, the bug flagged in #31028 was not detected...