Instructions to use rvcarung/ProxyType-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use rvcarung/ProxyType-9B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "rvcarung/ProxyType-9B") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from rvcarung/ProxyType-9B: direct link, hf CLI and curl.
- Browser
- Download file 657 Bytes
-
https://huggingface.co/rvcarung/ProxyType-9B/resolve/main/NOTICE
- Command line
-
hf download hf://rvcarung/ProxyType-9B/NOTICE
-
curl -L -o NOTICE https://huggingface.co/rvcarung/ProxyType-9B/resolve/main/NOTICE
657 Bytes
| ProxyType-9B is a LoRA adaptation of Qwen/Qwen3.5-9B. | |
| The Qwen Team provides the base model. | |
| The exact base revision is c202236235762e1c871ad0ccb60c8ee5ba337b9a. | |
| The base model source is https://huggingface.co/Qwen/Qwen3.5-9B/tree/c202236235762e1c871ad0ccb60c8ee5ba337b9a. | |
| LICENSE.base-model preserves the base model license text. | |
| ProxyBench trained separate adapter weights on accepted N-PX extraction answers. | |
| The tokenizer files preserve the exported training tokenizer and chat format. | |
| This repository does not include base weights, filings, accepted labels, or a merged model. | |
| Public license terms for the trained adapter and dataset remain undecided. | |