Instructions to use thenlpresearcher/mistral_sequence_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use thenlpresearcher/mistral_sequence_classification with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("mistralai/Mistral-7B-v0.3") model = PeftModel.from_pretrained(base_model, "thenlpresearcher/mistral_sequence_classification") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from thenlpresearcher/mistral_sequence_classification: direct link, hf CLI and curl.
- Browser
- Download file 1.67 kB
-
https://huggingface.co/thenlpresearcher/mistral_sequence_classification/resolve/main/README.md
- Command line
-
hf download hf://thenlpresearcher/mistral_sequence_classification/README.md
-
curl -L -o README.md https://huggingface.co/thenlpresearcher/mistral_sequence_classification/resolve/main/README.md
1.67 kB
metadata
library_name: peft
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.3
tags:
- generated_from_trainer
model-index:
- name: mistral_sequence_classification
results: []
mistral_sequence_classification
This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2667
- Pearson: 0.9704
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson |
|---|---|---|---|---|
| No log | 1.0 | 206 | 0.3305 | 0.9028 |
| No log | 2.0 | 412 | 0.2609 | 0.9532 |
| 0.4868 | 3.0 | 618 | 0.2432 | 0.9611 |
| 0.4868 | 4.0 | 824 | 0.2611 | 0.9639 |
| 0.0417 | 5.0 | 1030 | 0.2667 | 0.9704 |
Framework versions
- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.2.0
- Tokenizers 0.20.3