pygaggle
pygaggle copied to clipboard
castorini
a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
Error upon installation from git repo. Installation: ``` git clone --recursive https://github.com/castorini/pygaggle.git cd pygaggle/ pip install -r requirements.txt pip install -e /content/pygaggle ``` Code: ```py from pygaggle.rerank.base import Query, Text...
Hello, I was trying to evaluate the monot5-large model on the beir benchmark, but I noticed that the uploaded models - [10k ](https://huggingface.co/castorini/monot5-large-msmarco-10k)and [100k](https://huggingface.co/castorini/monot5-large-msmarco) models - has exactly the same...
When following the instruction in docs/experiments-finetune-monot5-gpu.md, a 'text' KeyError exception is raised. This fixes that issue.
Update `environment.yml` to work on m1 mac. ### Environment Device: MacBook Air (M2 chip) OS: MacOS Ventura 13.3 Using x86 Anaconda ### Testing Tried the Simple Reranking Example (https://github.com/castorini/pygaggle#a-simple-reranking-example) after...
Is there any plan to make the fine-tuning process of monoT5 & duoT5 public? We follow the steps in the paper to finetune the T5-base & T5-3B in pytorch framework...
Hello! I am trying to reproduce quality of monoT5 on [BEIR](https://github.com/beir-cellar/beir) benchmark from the recent [article](https://arxiv.org/pdf/2206.02873.pdf). But after running script `finetune_monot5.py` on one epoch, as stated in the description of...
Tried installing on colab notebook, Kaggle notebook, mac conda environment, windows conda environment but not able to install it properly. pip install -r requirements.txt conda env create -f environment.yml &&...
Hello, I tried to reproduce the result of monot5-large on the Dev set of MS MARCO passage dataset. I followed the exact same procedure in https://github.com/castorini/pygaggle/blob/master/docs/experiments-msmarco-passage-entire.md. I downloaded the data...
I am trying to install on colab notebook but facing following error. Kindly help me resolve the issue. /content WARNING: Skipping pygaggle as it is not installed. Cloning into 'pygaggle'......
For some reason when using the monoT5 reranker class to rerank results from a LuceneSearcher it assigns the same score to every document. I was able to fix this problem...
