Instructions to use mounimzad/BrainHR-Adapter-Research-Access with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mounimzad/BrainHR-Adapter-Research-Access with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct") model = PeftModel.from_pretrained(base_model, "mounimzad/BrainHR-Adapter-Research-Access") - Notebooks
- Google Colab
- Kaggle
BrainHR principal PEFT adapter
Access status β 2026-11-22
This minimal repository provides the principal BrainHR PEFT adapter through individual access requests with manual approval. Sign in to Hugging Face and request access. Approved users can download only the files present in this repository.
It contains adapter weights, the configuration, LICENSE, NOTICE and this model card. It contains no source implementation, training/evaluation scripts, dataset, CV text, annotation records or historical code revisions. The complete research repositories remain private.
The adapter is not a standalone merged model. It requires the separately licensed Meta-Llama-3-8B-Instruct base, reference revision 8afb486c1db24fe5011ec46dfbe5b5dccdb575c2, and PEFT-compatible software. Base weights are not redistributed here.
Adapter SHA-256: 20cfe4592625d5a507d75ed50dd5fa40f0ff006bfb760d36caea78e72feca900. This is the principal adapter, not the separate corrective adapter used in later anomaly experiments. No general production or recruitment-decision validation is claimed. See LICENSE and NOTICE.
- Downloads last month
- -
Model tree for mounimzad/BrainHR-Adapter-Research-Access
Base model
meta-llama/Meta-Llama-3-8B-Instruct