Update model config and readme

README.md

@@ -2,7 +2,7 @@
 language: 
 - en
 tags:
-- question-answering
+- qa
 - summarization
 - emotion-detection
 license: Apache 2.0
@@ -20,7 +20,7 @@ metrics:
 
 This model was finetuned on the CoQa, Squad 2, GoEmotions and CNN/DailyMail.
 
-It achieves a score of *F1 76.7* on the Squad 2 dev set and a score of *F1 68.5* on the CoQa dev set.
+It achieves a score of **F1 76.7** on the Squad 2 dev set and a score of **F1 68.5** on the CoQa dev set.
 
 Summarisation and emotion detection has not been evaluated yet.
 

README.md~

@@ -0,0 +1,81 @@
+---
+language: 
+- en
+tags:
+- question-answering
+- summarization
+- emotion-detection
+license: Apache 2.0
+datasets:
+- coqa
+- squad_v2
+- go_emotions
+- cnn_dailymail
+metrics:
+- f1
+---
+# T5 Base with QA + Summary + Emotion
+
+## Description
+
+This model was finetuned on the CoQa, Squad 2, GoEmotions and CNN/DailyMail.
+
+It achieves a score of **F1 76.7** on the Squad 2 dev set and a score of **F1 68.5** on the CoQa dev set.
+
+Summarisation and emotion detection has not been evaluated yet.
+
+## Usage
+
+### Question answering
+
+```python
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
+tokenizer = T5Tokenizer.from_pretrained("t5-base")
+
+def get_answer(question, prev_qa, context):
+    input_text = [f"q: {qa[0]} a: {qa[1]}" for qa in prev_qa]
+    input_text.append(f"q: {question}")
+    input_text.append(f"c: {context}")
+    input_text = " ".join(input_text)
+    features = tokenizer([input_text], return_tensors='pt')
+    tokens = model.generate(input_ids=features['input_ids'], 
+            attention_mask=features['attention_mask'], max_length=64)
+    return tokenizer.decode(tokens[0], skip_special_tokens=True)
+
+print(get_answer("Why is the moon yellow?", "I'm not entirely sure why the moon is yellow.")) # unknown
+
+context = "Elon Musk left OpenAI to avoid possible future conflicts with his role as CEO of Tesla."
+
+print(get_answer("Why not?", [("Does Elon Musk still work with OpenAI", "No")], context)) # to avoid possible future conflicts with his role as CEO of Tesla
+```
+
+### Summarisation
+
+```python
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
+tokenizer = T5Tokenizer.from_pretrained("t5-base")
+
+def summary(context):
+    input_text = f"summarize: {context}"
+    features = tokenizer([input_text], return_tensors='pt')
+    tokens = model.generate(input_ids=features['input_ids'], 
+            attention_mask=features['attention_mask'], max_length=64)
+    return tokenizer.decode(tokens[0], skip_special_tokens=True)
+```
+
+### Emotion detection
+
+```python
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
+tokenizer = T5Tokenizer.from_pretrained("t5-base")
+
+def emotion(context):
+    input_text = f"emotion: {context}"
+    features = tokenizer([input_text], return_tensors='pt')
+    tokens = model.generate(input_ids=features['input_ids'], 
+            attention_mask=features['attention_mask'], max_length=64)
+    return tokenizer.decode(tokens[0], skip_special_tokens=True)
+```

config.json

@@ -29,26 +29,8 @@
       "min_length": 30,
       "no_repeat_ngram_size": 3,
       "num_beams": 4,
-      "prefix": "summarize: "
+      "prefix": "summarise: "
     },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
   },
   "use_cache": true,
   "vocab_size": 32128

config.json~

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 32128
+}