Instructions to use GTimothee/sql-code-llama-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use GTimothee/sql-code-llama-4bits 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, "GTimothee/sql-code-llama-4bits") - Notebooks
- Google Colab
- Kaggle
File size: 133 Bytes
7f8e333 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:9481d32de09c007d2e13888540b19f82f5b1782c2aa470cc0ddbedafa66d6054
size 67143296
|