syssec-utd/pylingual-shared-lora-statement-3.14-v1

Python 3.14 LoRA for the frozen universal PyLingual statement backbone (shared-backbone + per-version LoRA study). The backbone and tokenizer are never modified; last-checkpoint/ holds the latest resumable adapter checkpoint while training runs and adapters/3.14/ plus family.json hold the final adapter.

  • Backbone: syssec-utd/pylingual-shared-statement-v1 at revision 3e42fd302a6aef684e3cf4748251bf716be99482, backbone_id 06ea40895d3bc927b75f1c559351691e9320db5479cecf74a9362fa2fd0878db
  • Data: syssec-utd/pylingual-shared-encoded-v1 adapter/3.14/statement/train at revision 0f70ef5ada329b652a6cd67502244db733f98109
  • Rank 64, alpha 128, dropout 0.05 on ['q', 'v']; opcode bindings {}
  • 2.0 epochs, batch 36 x 2 accumulation, learning rate 2e-05, FP16, seed 20261020
  • Code: https://github.com/quinntyx/pylingual branch feat-shared-backbone-lora, commit 02d9472a6c9dff726e3e56ee685d81872e91180b
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support