Table Question Answering
Transformers
Safetensors
Thai
English
llama
text-generation
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use AIAT/The_Scamper-opt70bqt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AIAT/The_Scamper-opt70bqt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("table-question-answering", model="AIAT/The_Scamper-opt70bqt")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AIAT/The_Scamper-opt70bqt") model = AutoModelForCausalLM.from_pretrained("AIAT/The_Scamper-opt70bqt") - Notebooks
- Google Colab
- Kaggle
Update README.md
#5
by suphanatwong - opened
README.md
CHANGED
|
@@ -37,10 +37,13 @@ pipeline_tag: table-question-answering
|
|
| 37 |
|
| 38 |
The Tubular Question Answering Large Language Model is based on OpenThaiGPT and fine-tuned for converting natural language questions into SQL queries. It learns to map the nuances of Thai language to SQL structures, enabling efficient retrieval of information from databases.
|
| 39 |
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
|
|
|
| 43 |
device_map="auto")
|
|
|
|
|
|
|
| 44 |
|
| 45 |
|
| 46 |
### Recommendations
|
|
|
|
| 37 |
|
| 38 |
The Tubular Question Answering Large Language Model is based on OpenThaiGPT and fine-tuned for converting natural language questions into SQL queries. It learns to map the nuances of Thai language to SQL structures, enabling efficient retrieval of information from databases.
|
| 39 |
|
| 40 |
+
```python
|
| 41 |
+
>>> model2_path ="AIAT/The_Scamper-opt70bqt"
|
| 42 |
+
>>> tokenizer = AutoTokenizer.from_pretrained(model2_path, padding_side="right",use_fast=False)
|
| 43 |
+
>>> model = AutoModelForCausalLM.from_pretrained(model2_path,
|
| 44 |
device_map="auto")
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
|
| 48 |
|
| 49 |
### Recommendations
|