Instructions to use NeuronTechnologiesAI/Neuron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use NeuronTechnologiesAI/Neuron with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/models/Qwen2.5-72B-Instruct") model = PeftModel.from_pretrained(base_model, "NeuronTechnologiesAI/Neuron") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-200/adapter_model.safetensors from NeuronTechnologiesAI/Neuron: direct link, hf CLI and curl.
- Browser
- Download file 1.68 GB
-
https://huggingface.co/NeuronTechnologiesAI/Neuron/resolve/main/checkpoint-200/adapter_model.safetensors
- Command line
-
hf download hf://NeuronTechnologiesAI/Neuron/checkpoint-200/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/NeuronTechnologiesAI/Neuron/resolve/main/checkpoint-200/adapter_model.safetensors
1.68 GB
- Xet hash:
- fed35ad9d25e18197df73bb50b59c0eb74497b3419a8dff748ea4a1c9b3a3796
- Size of remote file:
- 1.68 GB
- SHA256:
- 03486fa81540a78c84d8105e2aa9fde823b6f07625e9d39b66c725b8a0584cb3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.