Add README config

README.md

@@ -1,3 +1,13 @@
+---
+title: Autoprompt
+emoji: 🏢
+colorFrom: green
+colorTo: indigo
+sdk: streamlit
+app_file: app.py
+pinned: false
+---
+
 # AutoPrompt
 An automated method based on gradient-guided search to create prompts for a diverse set of NLP tasks. AutoPrompt demonstrates that masked language models (MLMs) have an innate ability to perform sentiment analysis, natural language inference, fact retrieval, and relation extraction. Check out our [website](https://ucinlp.github.io/autoprompt/) for the paper and more information.
 
@@ -49,17 +59,7 @@ Depending on the language model (i.e. BERT or RoBERTa) you choose to generate pr
 
 ### Sentiment Analysis
 ```
-python -m autoprompt.create_trigger \
-    --train glue_data/SST-2/train.tsv \
-    --dev glue_data/SST-2/dev.tsv \
-    --template '<s> {sentence} [T] [T] [T] [P] . </s>' \
-    --label-map '{"0": ["Ġworse", "Ġincompetence", "ĠWorse", "Ġblamed", "Ġsucked"], "1": ["ĠCris", "Ġmarvelous", "Ġphilanthrop", "Ġvisionary", "Ġwonderful"]}' \
-    --num-cand 100 \
-    --accumulation-steps 30 \
-    --bsz 24 \
-    --eval-size 48 \
-    --iters 180 \
-    --model-name roberta-large
+python -m autoprompt.create_trigger \\r\n    --train glue_data/SST-2/train.tsv \\r\n    --dev glue_data/SST-2/dev.tsv \\r\n    --template '<s> {sentence} [T] [T] [T] [P] . </s>' \\r\n    --label-map '{"0": ["Ġworse", "Ġincompetence", "ĠWorse", "Ġblamed", "Ġsucked"], "1": ["ĠCris", "Ġmarvelous", "Ġphilanthrop", "Ġvisionary", "Ġwonderful"]}' \\r\n    --num-cand 100 \\r\n    --accumulation-steps 30 \\r\n    --bsz 24 \\r\n    --eval-size 48 \\r\n    --iters 180 \\r\n    --model-name roberta-large
 ```
 
 ### Natural Language Inference
@@ -69,39 +69,12 @@ python  -m autoprompt.create_trigger  --train SICK_TRAIN_ALL_S.tsv --dev SICK_DE
 
 ### Fact Retrieval
 ```
-python -m autoprompt.create_trigger \
-    --train $path/train.jsonl \
-    --dev $path/dev.jsonl \
-    --template '<s> {sub_label} [T] [T] [T] [P] . </s>' \
-    --num-cand 10 \
-    --accumulation-steps 1 \
-    --model-name roberta-large \
-    --bsz 56 \
-    --eval-size 56 \
-    --iters 1000 \
-    --label-field 'obj_label' \
-    --tokenize-labels \
-    --filter \
-    --print-lama
+python -m autoprompt.create_trigger \\r\n    --train $path/train.jsonl \\r\n    --dev $path/dev.jsonl \\r\n    --template '<s> {sub_label} [T] [T] [T] [P] . </s>' \\r\n    --num-cand 10 \\r\n    --accumulation-steps 1 \\r\n    --model-name roberta-large \\r\n    --bsz 56 \\r\n    --eval-size 56 \\r\n    --iters 1000 \\r\n    --label-field 'obj_label' \\r\n    --tokenize-labels \\r\n    --filter \\r\n    --print-lama
 ```
 
 ### Relation Extraction
 ```
-python -m autoprompt.create_trigger \
-    --train $path/train.jsonl \
-    --dev $path/dev.jsonl \
-    --template '[CLS] {context} [SEP] {sub_label} [T] [T] [T] [P] . [SEP]' \
-    --num-cand 10 \
-    --accumulation-steps 1 \
-    --model-name bert-base-cased \
-    --bsz 32 \
-    --eval-size 32 \
-    --iters 500 \
-    --label-field 'obj_label' \
-    --tokenize-labels \
-    --filter \
-    --print-lama \
-    --use-ctx
+python -m autoprompt.create_trigger \\r\n    --train $path/train.jsonl \\r\n    --dev $path/dev.jsonl \\r\n    --template '[CLS] {context} [SEP] {sub_label} [T] [T] [T] [P] . [SEP]' \\r\n    --num-cand 10 \\r\n    --accumulation-steps 1 \\r\n    --model-name bert-base-cased \\r\n    --bsz 32 \\r\n    --eval-size 32 \\r\n    --iters 500 \\r\n    --label-field 'obj_label' \\r\n    --tokenize-labels \\r\n    --filter \\r\n    --print-lama \\r\n    --use-ctx
 ```
 
 ## Label Token Selection