asahi417 commited on
Commit
15c2cf7
1 Parent(s): a23ce8b

model update

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -21,7 +21,7 @@ widget:
21
  - text: "generate question: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, <hl> Cadillac Records <hl> ."
22
  example_title: "Question Generation Example 3"
23
  model-index:
24
- - name: lmqg/t5-large-subjqa-grocery
25
  results:
26
  - task:
27
  name: Text2text Generation
@@ -48,9 +48,9 @@ model-index:
48
  value: 63.41
49
  ---
50
 
51
- # Model Card of `lmqg/t5-large-subjqa-grocery`
52
  This model is fine-tuned version of [lmqg/t5-large-squad](https://huggingface.co/lmqg/t5-large-squad) for question generation task on the [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (dataset_name: grocery) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
53
- This model is continuously fine-tuned with [lmqg/t5-large-squad](https://huggingface.co/lmqg/t5-large-squad).
54
 
55
  ### Overview
56
  - **Language model:** [lmqg/t5-large-squad](https://huggingface.co/lmqg/t5-large-squad)
@@ -66,7 +66,7 @@ This model is continuously fine-tuned with [lmqg/t5-large-squad](https://hugging
66
  from lmqg import TransformersQG
67
 
68
  # initialize model
69
- model = TransformersQG(language="en", model="lmqg/t5-large-subjqa-grocery")
70
 
71
  # model prediction
72
  questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
@@ -77,7 +77,7 @@ questions = model.generate_q(list_context="William Turner was an English painter
77
  ```python
78
  from transformers import pipeline
79
 
80
- pipe = pipeline("text2text-generation", "lmqg/t5-large-subjqa-grocery")
81
  output = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
82
 
83
  ```
@@ -85,7 +85,7 @@ output = pipe("generate question: <hl> Beyonce <hl> further expanded her acting
85
  ## Evaluation
86
 
87
 
88
- - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/t5-large-subjqa-grocery/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_subjqa.grocery.json)
89
 
90
  | | Score | Type | Dataset |
91
  |:-----------|--------:|:--------|:-----------------------------------------------------------------|
@@ -119,7 +119,7 @@ The following hyperparameters were used during fine-tuning:
119
  - gradient_accumulation_steps: 32
120
  - label_smoothing: 0.15
121
 
122
- The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/t5-large-subjqa-grocery/raw/main/trainer_config.json).
123
 
124
  ## Citation
125
  ```
 
21
  - text: "generate question: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, <hl> Cadillac Records <hl> ."
22
  example_title: "Question Generation Example 3"
23
  model-index:
24
+ - name: lmqg/t5-large-subjqa-grocery-qg
25
  results:
26
  - task:
27
  name: Text2text Generation
 
48
  value: 63.41
49
  ---
50
 
51
+ # Model Card of `lmqg/t5-large-subjqa-grocery-qg`
52
  This model is fine-tuned version of [lmqg/t5-large-squad](https://huggingface.co/lmqg/t5-large-squad) for question generation task on the [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (dataset_name: grocery) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
53
+
54
 
55
  ### Overview
56
  - **Language model:** [lmqg/t5-large-squad](https://huggingface.co/lmqg/t5-large-squad)
 
66
  from lmqg import TransformersQG
67
 
68
  # initialize model
69
+ model = TransformersQG(language="en", model="lmqg/t5-large-subjqa-grocery-qg")
70
 
71
  # model prediction
72
  questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
 
77
  ```python
78
  from transformers import pipeline
79
 
80
+ pipe = pipeline("text2text-generation", "lmqg/t5-large-subjqa-grocery-qg")
81
  output = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
82
 
83
  ```
 
85
  ## Evaluation
86
 
87
 
88
+ - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/t5-large-subjqa-grocery-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_subjqa.grocery.json)
89
 
90
  | | Score | Type | Dataset |
91
  |:-----------|--------:|:--------|:-----------------------------------------------------------------|
 
119
  - gradient_accumulation_steps: 32
120
  - label_smoothing: 0.15
121
 
122
+ The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/t5-large-subjqa-grocery-qg/raw/main/trainer_config.json).
123
 
124
  ## Citation
125
  ```