mario-rc/emotional-rlaif-dpo-llama-3.2-3b-instruct

docs: correct project repository link

Reorder released models and apply requested card layout adjustments

Standardize License section while preserving base-model requirements

Add brief limitations introduction

Apply approved model-card format with model-specific data and examples

Restore original model-card text with explicitly requested updates

Record Hub-generated LFS attributes in release checksums

Publish verified emotional RLAIF adapter and unified 20-model card

Normalize model card tables

Upload updated SML emotional RLAIF adapter

Reorder model comparison tables

Polish training data paragraph

Fix remote code flags

Fix DPO data description

Adapt interactive prompt templates

Clarify training data sources

Normalize training data paragraph

Update usage examples

Fix training data description

Refine model card

Move training before evaluation and simplify metrics

Use one evaluation table for released models

Add evaluation section

Add project repository link

Add released emotional RLAIF model comparison table

Update model card title

Update model card after repository rename

Format dataset subset names in introduction

Standardize model details and training format

Clarify dataset usage in model card introduction

Simplify training procedure section

Link dataset in model card introduction

Standardize training and framework sections

Link training dataset in model card

Bold model card key-value labels

Normalize model card section order

Place intended use and limitations sections

Place framework versions after training procedure

Add simple and interactive usage examples

Reorder usage section and remove evaluation from model card

Append long usage example to model card

Unify model card template and add how-to-use section

Update model card

Upload final emotional RLAIF adapter files

initial commit