model update
Browse files
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:
|
25 |
results:
|
26 |
- task:
|
27 |
name: Text2text Generation
|
@@ -48,7 +48,7 @@ model-index:
|
|
48 |
value: 62.87
|
49 |
---
|
50 |
|
51 |
-
# Model Card of `
|
52 |
This model is fine-tuned version of [t5-base](https://huggingface.co/t5-base) for question generation task on the [lmqg/qg_squadshifts](https://huggingface.co/datasets/lmqg/qg_squadshifts) (dataset_name: new_wiki) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
53 |
|
54 |
|
@@ -66,7 +66,7 @@ This model is fine-tuned version of [t5-base](https://huggingface.co/t5-base) fo
|
|
66 |
from lmqg import TransformersQG
|
67 |
|
68 |
# initialize model
|
69 |
-
model = TransformersQG(language="en", model="
|
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", "
|
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/
|
89 |
|
90 |
| | Score | Type | Dataset |
|
91 |
|:-----------|--------:|:---------|:---------------------------------------------------------------------------|
|
@@ -119,7 +119,7 @@ The following hyperparameters were used during fine-tuning:
|
|
119 |
- gradient_accumulation_steps: 8
|
120 |
- label_smoothing: 0.15
|
121 |
|
122 |
-
The full configuration can be found at [fine-tuning config file](https://huggingface.co/
|
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: research-backup/t5-base-squadshifts-vanilla-new_wiki-qg
|
25 |
results:
|
26 |
- task:
|
27 |
name: Text2text Generation
|
|
|
48 |
value: 62.87
|
49 |
---
|
50 |
|
51 |
+
# Model Card of `research-backup/t5-base-squadshifts-vanilla-new_wiki-qg`
|
52 |
This model is fine-tuned version of [t5-base](https://huggingface.co/t5-base) for question generation task on the [lmqg/qg_squadshifts](https://huggingface.co/datasets/lmqg/qg_squadshifts) (dataset_name: new_wiki) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
53 |
|
54 |
|
|
|
66 |
from lmqg import TransformersQG
|
67 |
|
68 |
# initialize model
|
69 |
+
model = TransformersQG(language="en", model="research-backup/t5-base-squadshifts-vanilla-new_wiki-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", "research-backup/t5-base-squadshifts-vanilla-new_wiki-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/research-backup/t5-base-squadshifts-vanilla-new_wiki-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_squadshifts.new_wiki.json)
|
89 |
|
90 |
| | Score | Type | Dataset |
|
91 |
|:-----------|--------:|:---------|:---------------------------------------------------------------------------|
|
|
|
119 |
- gradient_accumulation_steps: 8
|
120 |
- label_smoothing: 0.15
|
121 |
|
122 |
+
The full configuration can be found at [fine-tuning config file](https://huggingface.co/research-backup/t5-base-squadshifts-vanilla-new_wiki-qg/raw/main/trainer_config.json).
|
123 |
|
124 |
## Citation
|
125 |
```
|