Commit History
-
Adding `safetensors` variant of this model
This is an automated PR created with https://huggingface.co/spaces/safetensors/convert This new file is equivalent to `pytorch_model.bin` but safe in the sense that no arbitrary code can be put into it. These files also happen to load much faster than their pytorch counterpart: https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb The widgets on your model page will run using this model even if this is not merged making sure the file actually works. If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions Feel free to ignore this PR.8452d5f
-
Blog post link
5493d5b
-
Initial README.md
b119bed -
Bake model with the latest https://huggingface.co/datasets/vblagoje/lfqa_support_docs
Using KILT's validation set and eval_downstream.py on model generations created by https://huggingface.co/spaces/lfqa/lfqa/blob/main/util/eval_generate.py we got KILT results: { 'downstream': { 'accuracy': 0.0, 'em': 0.0, 'f1': 0.27398557711151644, 'rougel': 0.24341652585508156}, 'kilt': { 'KILT-accuracy': 0.0, 'KILT-em': 0.0, 'KILT-f1': 0.02985996249488124, 'KILT-rougel': 0.027306950071259557}, 'retrieval': {'Rprec': 0.11235170969993022, 'recall@5': 0.1957431960921145}}a9cee57
-
Use KILT Wikipeda for support documents
5a7dd73
-
Don't use selftext in training
Clean questions and answersdda6460
-
Initialize model_max_length
60e1810 -
First working version, val_loss 2.91
55589f9
-
Initial version
261396d -
initial commit
f9ccfb9
