Instructions to use openbmb/MiniCPM3-RAG-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use openbmb/MiniCPM3-RAG-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM3-4B") model = PeftModel.from_pretrained(base_model, "openbmb/MiniCPM3-RAG-LoRA") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.model from openbmb/MiniCPM3-RAG-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 1.18 MB
-
https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA/resolve/refs%2Fpr%2F7/tokenizer.model
- Command line
-
hf download hf://openbmb/MiniCPM3-RAG-LoRA@refs/pr/7/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA/resolve/refs%2Fpr%2F7/tokenizer.model
1.18 MB
- Xet hash:
- f15194082adb5a8487f4d096130298abf3c880ee6f65d67ae4e70cb0cb812f82
- Size of remote file:
- 1.18 MB
- SHA256:
- bb74d51116831c3bf65db812c553f94ab0c88dcf97a5bbb37e3504f6d359c530
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.