-
_jaydesen created the following on Feb 01:_
Initial plan is to use a seq2seq pipeline over a set of supporting evidences.
An example of GooAQ dataset:
_Original issue: https://github.ibm.c…
-
I encountered the following error when running `python install.py`. All other model setups are fine (except attention_is_all_you_need because [www.quest.dcs.shef.ac.uk](http://www.quest.dcs.shef.ac.uk…
-
sentencepiece cannot load **jplu/tf-xlm-roberta-base/sentencepiece.bpe.model**
`Traceback (most recent call last):
File "/home/pcl_user/anaconda3/envs/fairseq/bin/bicleaner-ai-train", line 11, …
-
_franzm created the following on Apr 25:_
### Experiments with tinyXLMR (tinyxlmr-04192022) on the XOR TyDi task
Here are the initial results on using tinyXLMR on the XOR TyDi task. All resul…
-
Hi! I am trying to use a pretrained Sentenpiece model and running into some interesting normalization issues.
The code below shows how the single character showing continuation (three dots) is turn…
-
_franzm created the following on Feb 15:_
## Starting points
### mnlp-exp ColBERT repository in https://github.ibm.com/mnlp-exp/ColBERT
**Supports**
- additional representations (e.g. XLMR, …
-
_franzm created the following on Feb 15:_
## Starting points
### mnlp-exp ColBERT repository in https://github.ibm.com/mnlp-exp/ColBERT
**Supports**
- additional representations (e.g. XLMR, …
-
Hi,
I success to train an xlmr-base-20220411 Encoder Model according to README. When I tried to infer on the test set, the GPU memory usage keeps growing and cause a CUDA out-of-memory issue in the…
-
**Describe**
Model I am using MiniLM: The script is as follows
```
from fairseq.models.roberta import XLMRModel
from transformers import AutoTokenizer, AutoModel
xlmr = AutoModel.from_pretrained(…
-
Hi,
When I try to train an xlmr-base zero-shot encoder, a TypeError occurs. Here is the error message:
```
Traceback (most recent call last):
File "/home/massive/scripts/train.py", line 99, in…