Instructions to use jonathansuru/inkubalm-instruct-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jonathansuru/inkubalm-instruct-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("lelapa/InkubaLM-0.4B") model = PeftModel.from_pretrained(base_model, "jonathansuru/inkubalm-instruct-lora") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.model from jonathansuru/inkubalm-instruct-lora: direct link, hf CLI and curl.
- Browser
- Download file 991 kB
-
https://huggingface.co/jonathansuru/inkubalm-instruct-lora/resolve/main/tokenizer.model
- Command line
-
hf download hf://jonathansuru/inkubalm-instruct-lora/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/jonathansuru/inkubalm-instruct-lora/resolve/main/tokenizer.model
991 kB
- Xet hash:
- 03e1a90d17fd607eebe18a1af6e84de726b9b29dca5c375577efdffc913e0551
- Size of remote file:
- 991 kB
- SHA256:
- 1c41fcc6d44fcc4e8269e41dffe0123687baf800bd95a9c8b5d48abd9cb8971b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.