Instructions to use Fischerboot/Thinking-tiny-llama-v2-cp-3496 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Fischerboot/Thinking-tiny-llama-v2-cp-3496 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Aculi/Tinyllama-2B") model = PeftModel.from_pretrained(base_model, "Fischerboot/Thinking-tiny-llama-v2-cp-3496") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from Fischerboot/Thinking-tiny-llama-v2-cp-3496: direct link, hf CLI and curl.
- Browser
- Download file 1.45 GB
-
https://huggingface.co/Fischerboot/Thinking-tiny-llama-v2-cp-3496/resolve/main/optimizer.pt
- Command line
-
hf download hf://Fischerboot/Thinking-tiny-llama-v2-cp-3496/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Fischerboot/Thinking-tiny-llama-v2-cp-3496/resolve/main/optimizer.pt
1.45 GB
- Xet hash:
- 4fbd5519e6ed7ace95f2acc8dac7629d53e59431913e415131921fa289a5620f
- Size of remote file:
- 1.45 GB
- SHA256:
- 571c340935e72097d1a6723c13f5e542d1a54ecf74f72e7bb5059280dcead52a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.