Instructions to use Liu-Xiang/sql-code-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Liu-Xiang/sql-code-llama with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf") model = PeftModel.from_pretrained(base_model, "Liu-Xiang/sql-code-llama") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Liu-Xiang/sql-code-llama: direct link, hf CLI and curl.
- Browser
- Download file 2.45 kB
-
https://huggingface.co/Liu-Xiang/sql-code-llama/resolve/8bb02fef1a1fcd0bb73e45034fc202fc76933ea4/README.md
- Command line
-
hf download hf://Liu-Xiang/sql-code-llama@8bb02fef1a1fcd0bb73e45034fc202fc76933ea4/README.md
-
curl -L -o README.md https://huggingface.co/Liu-Xiang/sql-code-llama/resolve/8bb02fef1a1fcd0bb73e45034fc202fc76933ea4/README.md
2.45 kB
| license: llama2 | |
| library_name: peft | |
| tags: | |
| - generated_from_trainer | |
| base_model: codellama/CodeLlama-7b-hf | |
| model-index: | |
| - name: sql-code-llama | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # sql-code-llama | |
| This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4575 | |
| ## 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: 0.0003 | |
| - train_batch_size: 32 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 128 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_steps: 100 | |
| - training_steps: 400 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 2.2038 | 0.04 | 20 | 2.0534 | | |
| | 1.2229 | 0.07 | 40 | 0.8913 | | |
| | 0.8446 | 0.11 | 60 | 0.7965 | | |
| | 0.6032 | 0.14 | 80 | 0.5917 | | |
| | 0.3869 | 0.18 | 100 | 0.5647 | | |
| | 0.5675 | 0.22 | 120 | 0.5179 | | |
| | 0.4314 | 0.25 | 140 | 0.5061 | | |
| | 0.6327 | 0.29 | 160 | 0.5099 | | |
| | 0.4818 | 0.33 | 180 | 0.4879 | | |
| | 0.3499 | 0.36 | 200 | 0.4994 | | |
| | 0.5192 | 0.4 | 220 | 0.4810 | | |
| | 0.4056 | 0.43 | 240 | 0.4780 | | |
| | 0.5974 | 0.47 | 260 | 0.4846 | | |
| | 0.4665 | 0.51 | 280 | 0.4679 | | |
| | 0.3462 | 0.54 | 300 | 0.4755 | | |
| | 0.5084 | 0.58 | 320 | 0.4679 | | |
| | 0.3944 | 0.62 | 340 | 0.4617 | | |
| | 0.5776 | 0.65 | 360 | 0.4620 | | |
| | 0.4503 | 0.69 | 380 | 0.4587 | | |
| | 0.3444 | 0.72 | 400 | 0.4575 | | |
| ### Framework versions | |
| - PEFT 0.10.1.dev0 | |
| - Transformers 4.36.0 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 2.18.0 | |
| - Tokenizers 0.15.2 |