Ksukhantharat suphanatwong commited on
Commit
43a1854
1 Parent(s): ca80a23

Update README.md (#3)

Browse files

- Update README.md (162329af8c0e9cce3ffdd60812658c68ec82799a)


Co-authored-by: Suphanat Wongsanuphat <suphanatwong@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +15 -9
README.md CHANGED
@@ -15,7 +15,6 @@ pipeline_tag: table-question-answering
15
 
16
  <!-- Provide a quick summary of what the model is/does. -->
17
 
18
- This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
19
 
20
  ## Model Details
21
 
@@ -26,12 +25,10 @@ This modelcard aims to be a base template for new models. It has been generated
26
 
27
 
28
  - **Developed by:** The Scamper
29
- - **Funded by [optional]:** [More Information Needed]
30
- - **Shared by [optional]:** [More Information Needed]
31
  - **Model type:** Transformer
32
  - **Language(s) (NLP):** Thai, English
33
- - **License:** [More Information Needed]
34
- - **Finetuned from model [optional]:** OpenThaiGPT-1.0.0 70B (https://huggingface.co/openthaigpt/openthaigpt-1.0.0-70b-chat)
35
 
36
 
37
  ## Uses
@@ -70,13 +67,22 @@ Use the code below to get started with the model.
70
 
71
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
72
 
73
- #### Preprocessing [optional]
74
 
75
- [More Information Needed]
 
 
 
 
 
 
 
 
76
 
 
77
 
78
- #### Training Hyperparameters
79
 
80
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
81
 
82
 
 
15
 
16
  <!-- Provide a quick summary of what the model is/does. -->
17
 
 
18
 
19
  ## Model Details
20
 
 
25
 
26
 
27
  - **Developed by:** The Scamper
 
 
28
  - **Model type:** Transformer
29
  - **Language(s) (NLP):** Thai, English
30
+ - **License:** apache-2.0
31
+ - **Finetuned from model:** OpenThaiGPT-1.0.0 70B (https://huggingface.co/openthaigpt/openthaigpt-1.0.0-70b-chat)
32
 
33
 
34
  ## Uses
 
67
 
68
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
69
 
70
+ The methodology for fine-tuning involves a dataset with two columns: "question" and "SQL syntax". Here's a brief outline of the process:
71
 
72
+ 1. **Data Collection**: Gather a dataset containing pairs of questions and their corresponding SQL queries. Ensure the questions cover various topics and query types, while the SQL queries represent the desired actions on a database.
73
+
74
+ 2. **Pre-processing**: Clean and preprocess the data to remove noise, standardize formatting, and handle any inconsistencies. Tokenize the text and encode it into a format suitable for training.
75
+
76
+ 3. **Model Architecture**: Utilize OpenThaiGPT 1.0.0 70B as the base model.
77
+
78
+ 4. **Fine-tuning Setup**: Divide the dataset into training (90%) and test sets (10%). We define the training procedure, including hyperparameters such as learning rate, batch size, and number of training epochs.
79
+
80
+ 5. **Fine-tuning Process**: Train the model on the question-SQL pairs using the defined setup. During training, the model learns to predict the SQL query corresponding to a given question by minimizing a suitable loss function.
81
 
82
+ 6. **Testing**: Evaluate the final model on a held-out test set to assess its generalization performance on unseen data.
83
 
84
+ 7. **Deployment**: Deploy the fine-tuned model for text-to-SQL tasks in real-world applications, where it can generate SQL queries from natural language questions effectively and efficiently.
85
 
86
+ By following this methodology, the model can be fine-tuned to accurately convert natural language questions into SQL syntax, enabling seamless interaction with structured databases.
87
 
88