Instructions to use Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/akshat/work_collection/downloaded_Qwen2.5-3b-Instruct_model") model = PeftModel.from_pretrained(base_model, "Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter: direct link, hf CLI and curl.
- Browser
- Download file 7.39 MB
-
https://huggingface.co/Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/Username6568/Qwen2.5-3B-Instruct-1_plus_1_equals_1_adapter/resolve/main/adapter_model.safetensors
7.39 MB
- Xet hash:
- beec481f0c7308969e3865300c536463c8e5d13b441b295d834640fe2faf3833
- Size of remote file:
- 7.39 MB
- SHA256:
- 3b854ff43faf783699d672c90856af8bd1f9fcf34047af441f81c4145bb31b0d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.