Instructions to use gavinlaw/rasst-retriever-hn1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gavinlaw/rasst-retriever-hn1024 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("gavinlaw/rasst-retriever-hn1024", dtype="auto") - Notebooks
- Google Colab
- Kaggle
gavinlaw/rasst-retriever-hn1024
Public RASST release artifact used by the global-cache 30/30/20/20 main result.
- Manifest asset key:
retriever_hn1024 - Artifact type:
file - Original release source path:
/mnt/gemini/home/jiaxuanluo/train_outputs/q3rag_scale_lora-r128-tr128_bs8k_t=0.07_3var_gsv2full_gsdedup_varctx576_bs8k_gc128_wr1000k_m0.0_maxsim_mfa_variantE_hn1024_tcmoff_ep6_v3_smallest_dense_normAGGR_8gpu_aries_best_eval_acl6060_recallat10.pt - Manifest metadata:
source_run_id:lh1b88kw
This repository stores the MaxSim retriever checkpoint file used by RASST eval.
See the RASST repository for manifests and launch wrappers: https://github.com/luojiaxuan/RASST
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support