Instructions to use Jeesup/llama32-1B-sst2-int8-lora-seed42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Jeesup/llama32-1B-sst2-int8-lora-seed42 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B") model = PeftModel.from_pretrained(base_model, "Jeesup/llama32-1B-sst2-int8-lora-seed42") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from Jeesup/llama32-1B-sst2-int8-lora-seed42: direct link, hf CLI and curl.
- Browser
- Download file 13.6 MB
-
https://huggingface.co/Jeesup/llama32-1B-sst2-int8-lora-seed42/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://Jeesup/llama32-1B-sst2-int8-lora-seed42/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/Jeesup/llama32-1B-sst2-int8-lora-seed42/resolve/main/adapter_model.safetensors
13.6 MB
- Xet hash:
- 803ae2493b64ae6370a01d621d095f753979447ebd0018c91783c9fc305527e9
- Size of remote file:
- 13.6 MB
- SHA256:
- b55c5d1dbb763bd4d20cb63f8e884c984ef6628488a7cb51c984a249cfadb37d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.