Nicholas Broad
Nicholas Broad
I'm wondering what makes it incompatible with python 3.7 because that is the python version I am using and I can't upgrade to 3.8
# What does this PR do? The current implementations of DebertaForMaskedLM and DebertaV2ForMaskedLM do not load all of the weights from the checkpoints. After consulting the [original repo](https://github.com/microsoft/DeBERTa/blob/master/DeBERTa/deberta/bert.py), I modified...
I still have to do some tests, but I'm adding mlflow as a tracker. Feedback welcome!
# What does this PR do? Allows for more environment variables to be used with the `WandbCallback`. Prioritizes variables set in `TrainingArguments` ## Before submitting - [ ] This PR...
I made a custom model and I got this error: ``` RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that...
### System Info When trying to use this model ([ibm/re2g-reranker-trex](https://huggingface.co/ibm/re2g-reranker-trex)) in TEI, it will error because there is no tokenizer.json file. If I call `AutoTokenizer.from_pretrained("ibm/re2g-reranker-trex")`, there aren't any issues creating...
### Model description >We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the...
### Feature request Multi lora support in TGI has been around since 2.0.6, but it is not compatible with the Messages API using the openai package. ### Motivation The openai...
I'm assuming it only works on Ampere, Hopper, Lovelace. Is that correct? It might be nice to specify in the readme, if it is limited to certain GPU types.
I followed the steps in the DeBERTa guide to create the modified onnx file with the plugin. When I try using this model with triton inference server, it says >...