rust-bert
rust-bert copied to clipboard
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
The **Cross-Encoder for MS Marco** hugging face address is [here](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-12-v2) I want to use predict func like the followed python code: ``` from sentence_transformers import CrossEncoder model = CrossEncoder('model_name', max_length=512)...
Fine-tuning Marian model use huggingface transformers library. Translate model to rust_model.ot format. Can't use pipelien translate. This is the erroer message. >Tch tensor error: cannot find the tensor named model.decoder.embed_positions.weight...
I've been reading the code, but unsure if sequence classification is supported in some undocumented way with ELECTRA?
In the interests of simplicity, it would be nice of rust-bert directly supported the [torch.load](https://pytorch.org/docs/stable/generated/torch.load.html) format. Is this not already the case simply because `torch.load` requires python pickle? If that's...
Can we show some love for the Mac M1 people out there? MPS doesn't seem any harder to choose if available than CUDA, and tch-rs seems to include it in...
## Problem All the examples I've tried crash when loading the model using the pytorch-rocm gpu package, I know this is unsupported (as in not mentioned in the README), but...
I am looking into adding support for sentence-transformers/all-mpnet-base-v2. I have successfully extracted the rust weights and the models are here - https://huggingface.co/diptanuc/all-mpnet-base-v2 The SentenceEmbeddingBuilder doesn't however understand the mpnet architecture....
Hi, congratulations on the project! I'm trying to port my Python project to Rust, in my case I use the model (bert_uncased_L-12_H-768_A-12)! Does this model work with rust-bert? https://huggingface.co/google/bert_uncased_L-12_H-768_A-12 Thanks,...
Hi, thanks so much for the great project! At the moment `TranslationModel::translate` takes a slice of texts to translate, a source language and a destination language and produces a slice...
Hi @guillaume-be! How hard would it be to add support for [GODEL](https://github.com/microsoft/GODEL)? It is the [natural successor to DialoGPT](https://github.com/microsoft/DialoGPT#a-state-of-the-art-large-scale-pretrained-response-generation-model-dialogpt), so would it be of similar effort to #57?