mauryaland

Installable pip package

5

Hello, Thank you for these great embeddings, really nice to have the possibility to use them, especially the french one in my case. I wonder if you are planning to...

### Feature request Take into account the parameter num_return_sequences to get multiple outputs ### Motivation In order to propose multiple choices to a user, using the parameter num_return_sequences is very...

There was a bug where in a batch, it took the last tag sequence of that batch from the Viterbi decoder instead of the tag sequence corresponding to its sentence.

[Feature]: Pin torch>=2.x to use torch.compile

1

### Problem statement Get benefits from features of torch>=2.x ### Solution Pin torch version to >=2.x to use torch.compile on models ### Additional Context _No response_

Mistral model with a modified tokenizer gives ParserError

2

**The bug** I have fine tuned a mistral 7b v3 on this dataset https://huggingface.co/datasets/maurya/alpaca_ccass_motivations_sommaires_titres which includes special tokens that need to be added to the tokenizer as mentioned in the...

### Category Dataset ### Description Hi, at the Cour de cassation, we have published two interesting datasets on HuggingFace: - [Court decisions similarity dataset](https://huggingface.co/datasets/Cour-de-cassation/ccass_rapprochements_sommaires_with_sources) - [Summary and keyword generation from...