Instructions to use cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1") model = PeftModel.from_pretrained(base_model, "cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL: direct link, hf CLI and curl.
- Browser
- Download file 1.89 kB
-
https://huggingface.co/cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL/resolve/main/README.md
- Command line
-
hf download hf://cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL/README.md
-
curl -L -o README.md https://huggingface.co/cnatale/Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL/resolve/main/README.md
1.89 kB
metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL
results: []
Mistral-7B-Instruct-v0_1-Txt-2-Presto-SQL
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.6454
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 80
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3516 | 0.71 | 10 | 1.0778 |
| 1.0131 | 1.43 | 20 | 0.8707 |
| 0.8446 | 2.14 | 30 | 0.7695 |
| 0.7563 | 2.86 | 40 | 0.7202 |
| 0.7009 | 3.57 | 50 | 0.6803 |
| 0.6368 | 4.29 | 60 | 0.6585 |
| 0.6201 | 5.0 | 70 | 0.6473 |
| 0.5755 | 5.71 | 80 | 0.6454 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0