Spaces:
Sleeping
Sleeping
Merge branch 'main' of https://github.com/anakin87/who-killed-laura-palmer
Browse files
README.md
CHANGED
@@ -22,8 +22,8 @@ WKLP is a simple Question Answering system, based on data crawled from [Twin Pea
|
|
22 |
|
23 |
- [Project architecture π§±](#project-architecture-)
|
24 |
- [What can I learn from this project? π](#what-can-i-learn-from-this-project-)
|
25 |
-
- [Installation π»](#installation-)
|
26 |
- [Repository structure π](#repository-structure-)
|
|
|
27 |
- [Possible improvements β¨](#possible-improvements-)
|
28 |
---
|
29 |
|
@@ -71,7 +71,7 @@ To run the web app, simply type: `streamlit run app.py`
|
|
71 |
- Streamlit web app
|
72 |
### Reader
|
73 |
- The reader model (`deepset/roberta-base-squad2`) is a good compromise between speed and accuracy, running on CPU. There are certainly better (and more computationally expensive) models, as you can read in the [Haystack documentation](https://haystack.deepset.ai/pipeline_nodes/reader).
|
74 |
-
- You can also think about preparing a Twin Peaks QA dataset and fine-
|
75 |
|
76 |
|
77 |
|
|
|
22 |
|
23 |
- [Project architecture π§±](#project-architecture-)
|
24 |
- [What can I learn from this project? π](#what-can-i-learn-from-this-project-)
|
|
|
25 |
- [Repository structure π](#repository-structure-)
|
26 |
+
- [Installation π»](#installation-)
|
27 |
- [Possible improvements β¨](#possible-improvements-)
|
28 |
---
|
29 |
|
|
|
71 |
- Streamlit web app
|
72 |
### Reader
|
73 |
- The reader model (`deepset/roberta-base-squad2`) is a good compromise between speed and accuracy, running on CPU. There are certainly better (and more computationally expensive) models, as you can read in the [Haystack documentation](https://haystack.deepset.ai/pipeline_nodes/reader).
|
74 |
+
- You can also think about preparing a Twin Peaks QA dataset and fine-tuning the reader model to get better accuracy, as explained in this [Haystack tutorial](https://haystack.deepset.ai/tutorials/fine-tuning-a-model).
|
75 |
|
76 |
|
77 |
|