Model card v3: step-by-step gated-access walkthrough, separate GPU/CPU quickstarts with hardware requirements, batch processing with tqdm progress bar

Model card v2: empirically verified instructions (tested on transformers 5.12/peft 0.19 and 4.38/0.7.1), corrected storage-format description, verified example outputs, dependency matrix

Update tokenizer.json (modern PEFT format conversion)

Convert adapter to modern PEFT format (merged trained score head). Verified logit-equivalent to the PEFT 0.7.1 original on both transformers 5.12/peft 0.19 and transformers 4.38/peft 0.7.1 stacks. Original-format files remain in git history.

Update adapter_config.json (modern PEFT format conversion)

Add complete model card: pipeline overview, adapter/full-model explanation, download and usage instructions with exact prompt formats and label mappings

Upload complete local adapter: fp32 weights incl. trained score base_layer, tokenizer files, and PEFT model card

Upload LlamaForSequenceClassification

initial commit