Upload 10 files

.idea/gpt-2.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="JavaScriptSettings">
+    <option name="languageLevel" value="ES6" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (GradioHub)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/gpt-2.iml" filepath="$PROJECT_DIR$/.idea/gpt-2.iml" />
+    </modules>
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectId" id="1dgdlLVrrVfgwRsipZaHeoQG6FQ" />
+</project>

README.md

@@ -1,13 +1,7 @@
----
-title: Gpt2 Sharjeel
-emoji: 🐠
-colorFrom: red
-colorTo: yellow
-sdk: gradio
-sdk_version: 4.8.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
+# GPT-2 on Gradio
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+![alt text](https://github.com/gradio-app/gpt-2/blob/master/screenshots/interface.png?raw=true)
+
+- Loads `gpt-2`, but can load `gpt2-medium`, `gpt2-large` or `gpt2-xl`.
+- `max_length` set to 100 (The max length of the sequence to be generated.)
+- running `".".join(output.split(".")[:-1]) + "."` so that `max_length` doesn't stop an output abruptly. 

gpt.py

@@ -0,0 +1,9 @@
+from transformers import TFGPT2LMHeadModel, GPT2Tokenizer
+import tensorflow
+
+
+def get_model(name="gpt2"):
+    tokenizer = GPT2Tokenizer.from_pretrained(name)
+    model = TFGPT2LMHeadModel.from_pretrained(name,
+                                      pad_token_id=tokenizer.eos_token_id)
+    return model, tokenizer

requirements.txt

@@ -0,0 +1,2 @@
+tensorflow==2.1
+transformers

run-gradio.py

@@ -0,0 +1,24 @@
+import gradio
+from gpt import get_model
+
+
+model, tokenizer = get_model()
+
+def predict(inp):
+    input_ids = tokenizer.encode(inp, return_tensors='tf')
+    beam_output = model.generate(input_ids, max_length=100, num_beams=5,
+                                 no_repeat_ngram_size=2, early_stopping=True)
+    output = tokenizer.decode(beam_output[0], skip_special_tokens=True,
+                              clean_up_tokenization_spaces=True)
+    return ".".join(output.split(".")[:-1]) + "."
+
+ 
+
+INPUTS = gradio.inputs.Textbox()
+OUTPUTS = gradio.outputs.Textbox()
+INTERFACE = gradio.Interface(fn=predict, inputs=INPUTS, outputs=OUTPUTS, title="GPT-2",
+                 description="GPT-2 is a large transformer-based language model with 1.5 billion parameters, trained on a dataset[1] of 8 million web pages. GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text.",
+                 thumbnail="https://github.com/gradio-app/gpt-2/raw/master/screenshots/interface.png?raw=true",
+                 capture_session=False)
+
+INTERFACE.launch(inbrowser=True)