Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
# Mistral fine-tuned to Multi-NLI (MNLI
|
| 7 |
+
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.
|
| 8 |
+
|
| 9 |
+
## Model Details
|
| 10 |
+
- Base model: [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
|
| 11 |
+
- Training data: [MNLI](https://huggingface.co/datasets/multi_nli)
|
| 12 |
+
- Training details: QloRA finetuning, num_epochs = 3
|