ord-retro-qwen25-15b LoRA adapter

QLoRA adapter fine-tuned on ORD-derived single-step reaction records.

Task:

target molecule SMILES -> one single-step JSON synthesis proposal.

Training setup:

  • Base model: Qwen/Qwen2.5-1.5B-Instruct
  • Max sequence length: 2048
  • Max steps: 2500
  • LoRA rank: 32
  • BF16: True

Limitations:

  • Academic/diploma demonstration only.
  • Not authoritative chemistry guidance.
  • Product-only retrosynthesis is under-constrained.
  • Generated routes must be manually checked.
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. 🙋 Ask for provider support

Model tree for oleh13/ord-retro-qwen25-15b-lora

Adapter
(1372)
this model