Instructions to use themanas-superrep/superrep-mail with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use themanas-superrep/superrep-mail with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model = PeftModel.from_pretrained(base_model, "themanas-superrep/superrep-mail") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from themanas-superrep/superrep-mail: direct link, hf CLI and curl.
- Browser
- Download file 1.56 kB
-
https://huggingface.co/themanas-superrep/superrep-mail/resolve/main/README.md
- Command line
-
hf download hf://themanas-superrep/superrep-mail/README.md
-
curl -L -o README.md https://huggingface.co/themanas-superrep/superrep-mail/resolve/main/README.md
1.56 kB
metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: superrep-mail
results: []
superrep-mail
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4014
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1186 | 1.0 | 1 | 2.7996 |
| 0.6556 | 1.3333 | 2 | 2.4014 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1