romrawinjp
commited on
Commit
•
13857fe
1
Parent(s):
83df6ab
Update README.md
Browse files
README.md
CHANGED
@@ -8,9 +8,16 @@ language:
|
|
8 |
pipeline_tag: text-generation
|
9 |
tags:
|
10 |
- code_generation
|
|
|
11 |
---
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
```python
|
15 |
from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaTokenizer
|
16 |
import pandas as pd
|
@@ -38,4 +45,10 @@ prompt = f"""
|
|
38 |
tokens = tokenizer(prompt, return_tensors="pt")
|
39 |
output = model.generate(tokens["input_ids"], max_new_tokens=20, eos_token_id=tokenizer.eos_token_id)
|
40 |
print(get_prediction(tokenizer.decode(output[0], skip_special_tokens=True)))
|
41 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
pipeline_tag: text-generation
|
9 |
tags:
|
10 |
- code_generation
|
11 |
+
- sql
|
12 |
---
|
13 |
|
14 |
+
# 🤖 [Super AI Engineer Development Program Season 4](https://superai.aiat.or.th/) - Pangpuriye Table-based Question Answering Model
|
15 |
+
|
16 |
+
![logo](https://huggingface.co/datasets/AIAT/Pangpuriye-generated_by_typhoon/resolve/main/logo/logo.png)
|
17 |
+
|
18 |
+
This model was fine-tuned from the original [OpenThaiGPT-1.0.1-7b](https://huggingface.co/openthaigpt/openthaigpt-1.0.0-7b-chat). The model is set under Apache license 2.0.
|
19 |
+
|
20 |
+
## Example inference using huggingface transformers.
|
21 |
```python
|
22 |
from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaTokenizer
|
23 |
import pandas as pd
|
|
|
45 |
tokens = tokenizer(prompt, return_tensors="pt")
|
46 |
output = model.generate(tokens["input_ids"], max_new_tokens=20, eos_token_id=tokenizer.eos_token_id)
|
47 |
print(get_prediction(tokenizer.decode(output[0], skip_special_tokens=True)))
|
48 |
+
```
|
49 |
+
|
50 |
+
## Acknowledgements
|
51 |
+
|
52 |
+
The dataset is collectively stored by the members of Panguriye's house during the LLMs hackathon in Super AI Engineer Development Program Season 4.
|
53 |
+
|
54 |
+
We thank the organizers of this hackathon, [OpenThaiGPT](https://openthaigpt.aieat.or.th/), [AIAT](https://aiat.or.th/), [NECTEC](https://www.nectec.or.th/en/) and [ThaiSC](https://thaisc.io/) for this challenging task and opportunity to be a part of developing Thai large language model.
|