Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
---
|
| 7 |
+
# Gemma fine-tuned to Multi-NLI (MNLI
|
| 8 |
+
This model is for Textual Entailment (NLI), i.e., predict whether sentence 1 is supported by sentence 2. It's a 3-way classification where the relationship between sentence 1 and sentence 2 can be entailment, neutral, contradiction.
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
- Base model: [gemma-7b-aps-it](https://huggingface.co/google/gemma-7b-aps-it)
|
| 12 |
+
- Training data: [MNLI](https://huggingface.co/datasets/multi_nli)
|
| 13 |
+
- Training details: QLoRA fine tuning, num_epochs = 3
|
| 14 |
+
|