Instructions to use Predacon/pico-lamma-3.2-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Predacon/pico-lamma-3.2-checkpoint with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct") model = PeftModel.from_pretrained(base_model, "Predacon/pico-lamma-3.2-checkpoint") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from Predacon/pico-lamma-3.2-checkpoint: direct link, hf CLI and curl.
- Browser
- Download file 11.5 MB
-
https://huggingface.co/Predacon/pico-lamma-3.2-checkpoint/resolve/main/optimizer.pt
- Command line
-
hf download hf://Predacon/pico-lamma-3.2-checkpoint/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Predacon/pico-lamma-3.2-checkpoint/resolve/main/optimizer.pt
11.5 MB
- Xet hash:
- bd794f114be20d09a74f5b1c336cea2e2e5df5a9448439bca8791c6d86b80aa1
- Size of remote file:
- 11.5 MB
- SHA256:
- 4278ff1728a97256ec93059dda29e374434a3ab73bba98ec0afdd6041fc09e2a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.