Update

.gitattributes

@@ -1,27 +1,27 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,37 @@
 ---
-title: Realm
-emoji: 😻
+title: REALM Demo
+emoji: 💻
 colorFrom: pink
 colorTo: green
 sdk: gradio
-sdk_version: 2.8.9
 app_file: app.py
 pinned: false
-license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+ 
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import numpy as np
+import torch
+from transformers import RealmForOpenQA, RealmRetriever
+
+model_name = "google/realm-orqa-nq-openqa"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+retriever = RealmRetriever.from_pretrained(model_name)
+tokenizer = retriever.tokenizer
+openqa = RealmForOpenQA.from_pretrained(model_name, retriever=retriever)
+openqa.to(device)
+default_num_block_records = openqa.config.num_block_records
+
+def add_additional_documents(openqa, additional_documents):
+    documents = additional_documents.split("\n")
+    np_documents = np.array([doc.encode() for doc in  documents], dtype=object)
+    
+    total_documents = np_documents.shape[0]
+
+    retriever = openqa.retriever
+    tokenizer = openqa.retriever.tokenizer
+    
+    # docs
+    retriever.block_records = np.concatenate((retriever.block_records[:default_num_block_records], np_documents), axis=0)
+
+    # embeds
+    inputs = tokenizer(documents, padding=True, truncation=True, return_tensors="pt").to(device)
+
+    with torch.no_grad():
+        projected_score = openqa.embedder(**inputs, return_dict=True).projected_score
+        openqa.block_emb = torch.cat((openqa.block_emb[:default_num_block_records], projected_score), dim=0)
+
+    openqa.config.num_block_records = default_num_block_records + total_documents
+
+def question_answer(question, additional_documents):
+    question_ids = tokenizer(question, return_tensors="pt").input_ids
+
+    if additional_documents != "":
+        add_additional_documents(openqa, additional_documents)
+        
+    with torch.no_grad():
+        outputs = openqa(input_ids=question_ids.to(device), return_dict=True)
+
+    return tokenizer.decode(outputs.predicted_answer_ids)
+
+
+additional_documents_input = gr.inputs.Textbox(lines=5, placeholder="Each line represents a document entry. Leave blank to use default wiki documents.")
+
+iface = gr.Interface(
+    fn=question_answer,
+    inputs=["text", additional_documents_input],
+    outputs=["textbox"],
+    allow_flagging="never"
+)
+iface.launch(enable_queue=True)

requirements.txt

@@ -0,0 +1,3 @@
+numpy
+torch
+transformers