Download THIRD_PARTY.md from GoatHerder/Ariadne-Laya-Support: direct link, hf CLI and curl.
- Browser
- Download file 1.8 kB
-
https://huggingface.co/GoatHerder/Ariadne-Laya-Support/resolve/main/THIRD_PARTY.md
- Command line
-
hf download hf://GoatHerder/Ariadne-Laya-Support/THIRD_PARTY.md
-
curl -L -o THIRD_PARTY.md https://huggingface.co/GoatHerder/Ariadne-Laya-Support/resolve/main/THIRD_PARTY.md
Sources and attribution
Shared model
This interface uses convaiinnovations/laya at revision 55cf4c4ebb4ebe31b2550e8bdf3bd21b99753851. The runtime downloads and caches the base separately. Original Laya embeddings, encoder blocks and decision heads remain frozen.
Software
Ariadne's runtime, prompts and benchmark preparation use code or recipes adapted from:
- NandhaKishorM/laya, commit
4066d5d5fbf08b66c6757ddeedbd797bd7655bc0, Apache-2.0. Notice: licenses/laya-LICENSE. - AbdelStark/jev-benchmarks, commit
0d610cc53e79bcbec691312b0c4adb4a0e371642, Apache-2.0. Notice: licenses/jev-benchmarks-LICENSE.
Ariadne's license is in LICENSE. Other installed dependencies retain their own licenses. Independent adaptation; no affiliation with or endorsement by the source authors.
Training data and evaluation
Dataset: bitext/Bitext-customer-support-llm-chatbot-training-dataset, revision 430d1a89bd93bd1fa23c16f29dd53e73f0087443. Dataset metadata is preserved in source.json. The dataset retains its own license; training data is not included in this package.
See README.md for task scope and comparison limitations, and metrics.json for the public comparison model's revision and evaluation details. Public comparison weights are not included.