-
## 🚀 Feature
HF transformers implements 8 bit and 4 bit quantization. It would be nice if that feature can be leveraged for the xlm-r-xxl machine translation eval model.
### Motivation
The lar…
-
python finetune/run_classifier.py --pretrained_model_path models/roberta-base-finetuned-dianping-chinese/pytorch_model.bin \
--vocab_path models/google_zh_vocab.txt…
-
## âť“ Questions and Help
### Before asking:
1. Search for similar [issues](https://github.com/Unbabel/COMET/issues).
3. Search the [docs](https://unbabel.github.io/COMET/html/index.html).
…
-
### System Info
I have trained a model and am now trying to load and quantise it but getting the error:
BertForSequenceClassification does not support 'device_map':"auto" yet
Code for loading …
-
I have to say, that is quote astonishing how fast here everythings moves forward, and also the community!
If you pause for 1 month, you feel you get lost with the whole progress. :)
My experiments…
-
### Describe the issue
cuda 10.2
onnx=1.8
onnxruntime-gpu=1.6
For sequnce labeling task (input the token ids, output the start_pos, end_pos), the pytorch use 1.8G, but onnx use 1.9G (although …
-
Is it possible to use a different tokenizer with multiple language support for the Donut processor? like mbart tokenizer in the Donut processor instead of xlmrobertafast
@NielsRogge
-
Fine tune 3 (or more) popular models and compare performance to DistilBERT for the movie sentiment analysis task.
Some choices:
GPT-3
LaMDA
Turing-NLG
XGen
Llama 2 (7 billion)
Gemini
Pic…
-
@dirkneuhaeuser Thanks for making the world a better place, your classifier is extremely helpful for natural language understanding.
Unfortunately, 91% accuracy is still not really great for widespre…
-
Hi @frankaging ,
when i run causal_training.py
i have Error: forward() got an unexpected keyword argument 'interchanged_variables'
log
`01/14/2022 07:41:12 - INFO - utils - PID: 2342567 - Using M…