|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
|
|
|
|
|
|
# Mistral fine-tuned to Multi-NLI (MNLI |
|
|
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. |
|
|
|
|
|
## Model Details |
|
|
- Base model: [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) |
|
|
- Training data: [MNLI](https://huggingface.co/datasets/multi_nli) |
|
|
- Training details: QloRA finetuning, num_epochs = 3 |
|
|
|
