Instructions to use Shibyan/llama3.1_Odata2SQL-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Shibyan/llama3.1_Odata2SQL-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "Shibyan/llama3.1_Odata2SQL-lora") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-30/optimizer.pt from Shibyan/llama3.1_Odata2SQL-lora: direct link, hf CLI and curl.
- Browser
- Download file 168 MB
-
https://huggingface.co/Shibyan/llama3.1_Odata2SQL-lora/resolve/main/checkpoint-30/optimizer.pt
- Command line
-
hf download hf://Shibyan/llama3.1_Odata2SQL-lora/checkpoint-30/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Shibyan/llama3.1_Odata2SQL-lora/resolve/main/checkpoint-30/optimizer.pt
168 MB
- Xet hash:
- 3268721b0a3841adaaa448984f4ea68c11c0636fbb273fcab912e9211650dcae
- Size of remote file:
- 168 MB
- SHA256:
- c07a316240a2da61552ea2e62c49fd3b05f8af93eb36af27e52fafae1502239c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.