32 lines
1.1 KiB
Markdown
32 lines
1.1 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
base_model: dicta-il/dictalm2.0-instruct
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- he
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
# Model Card for Guysh1805/dictalm2-it-qa-fine-tune
|
||
|
|
|
||
|
|
This is a fine-tuned version of the Dicta-IL dictalm2.0-instruct model, specifically tailored for generating question-answer pairs in Hebrew.
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
### Model Description
|
||
|
|
The model, Guysh1805/dictalm2-it-qa-fine-tunetuned, is a fine-tuned version of the dictalm2.0-instruct model on a both synthetically generated datasets and already existing Q&A datasets wrapped in insturction prompts.
|
||
|
|
|
||
|
|
- **Developed by:** Guy Shapira
|
||
|
|
- **Model type:** Transformer-based, fine-tuned Dicta-IL dictalm2.0-instruct
|
||
|
|
- **Language(s) (NLP):** Hebrew
|
||
|
|
- **Finetuned from:** dicta-il/dictalm2.0-instruct
|
||
|
|
|
||
|
|
## How to Get Started with the Model
|
||
|
|
To get started, load the model using the Transformers library by Hugging Face:
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
|
||
|
|
|
||
|
|
model_name = "Guysh1805/dictalm2-it-qa-fine-tune"
|
||
|
|
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
```
|