Instructions to use HL02/tora-code-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HL02/tora-code-7b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("llm-agents/tora-code-7b-v1.0") model = PeftModel.from_pretrained(base_model, "HL02/tora-code-7b") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from HL02/tora-code-7b: direct link, hf CLI and curl.
- Browser
- Download file 16.8 MB
-
https://huggingface.co/HL02/tora-code-7b/resolve/main/adapter_model.bin
- Command line
-
hf download hf://HL02/tora-code-7b/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/HL02/tora-code-7b/resolve/main/adapter_model.bin
16.8 MB
- Xet hash:
- 86612737320ec8533adbbd0454762fd19e3c22742d82140326318cce49a3d533
- Size of remote file:
- 16.8 MB
- SHA256:
- b600814e2bca8775b1511e09f146b93acb4fd52e808823fe51b593367086ebda
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.