Question Answering
Transformers
Safetensors
English
llama
text-generation
rag
text-generation-inference
Instructions to use DISLab/Ext2Gen-8B-R2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DISLab/Ext2Gen-8B-R2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="DISLab/Ext2Gen-8B-R2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DISLab/Ext2Gen-8B-R2") model = AutoModelForCausalLM.from_pretrained("DISLab/Ext2Gen-8B-R2") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -90,6 +90,19 @@ Answer: Your Answer
|
|
| 90 |
```
|
| 91 |
|
| 92 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
### Performance Benchmark
|
| 95 |
Our evaluations demonstrate that Ext2Gen-8B-R2 significantly enhances robustness in RAG systems:
|
|
|
|
| 90 |
```
|
| 91 |
|
| 92 |
|
| 93 |
+
Note that this prompt outputs both extracted relevant sentences and the answer to the query.
|
| 94 |
+
|
| 95 |
+
The output follows a consistent format as seen in an example below.
|
| 96 |
+
|
| 97 |
+
```
|
| 98 |
+
Extracted Sentences:
|
| 99 |
+
- The estimated number of deaths is 150-300,000, mainly Jews.
|
| 100 |
+
|
| 101 |
+
Answer: The estimated number of deaths at Chelmno is 150-300,000, mainly Jews.
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
The number of extracted sentences vary depending on the QA.
|
| 105 |
+
|
| 106 |
|
| 107 |
### Performance Benchmark
|
| 108 |
Our evaluations demonstrate that Ext2Gen-8B-R2 significantly enhances robustness in RAG systems:
|