Group Relative Policy Optimization fine-tunes for DialLM across Gemma, Llama, and Qwen models, covering all dialect variants.
Jordan Painter
jordanpainter
AI & ML interests
None yet
Recent Activity
updated a model 26 days ago
jordanpainter/diallm-llama-base-sft-ind published a model 26 days ago
jordanpainter/diallm-llama-base-sft-ind updated a model 26 days ago
jordanpainter/diallm-llama-base-sft-britOrganizations
models 56
jordanpainter/diallm-llama-base-sft-ind
8B • Updated • 26
jordanpainter/diallm-llama-base-sft-brit
8B • Updated • 26
jordanpainter/diallm-llama-base-sft-aus
8B • Updated • 27
jordanpainter/sft-llama-base-aus
Updated
jordanpainter/diallm-dialect-classifier
Text Classification • 0.2B • Updated • 7
jordanpainter/diallm-qwen-gspo-all
Text Generation • 8B • Updated • 98
jordanpainter/diallm-qwen-grpo-all
Text Generation • 8B • Updated • 64 • 1
jordanpainter/diallm-qwen-grpo-ind
Text Generation • 8B • Updated • 87
jordanpainter/diallm-qwen-grpo-brit
Text Generation • 8B • Updated • 89
jordanpainter/diallm-qwen-grpo-aus
Text Generation • 8B • Updated • 88
datasets 8
jordanpainter/dialect-llama-base-all
Preview • Updated • 6
jordanpainter/dialect-qwen-base-all
Preview • Updated • 7
jordanpainter/dialect-gemma-base-all
Preview • Updated • 6
jordanpainter/base_outputs_qwen_all
Updated • 3
jordanpainter/alignment-indian-final
Viewer • Updated • 18.4k • 6
jordanpainter/alignment-british-final
Viewer • Updated • 15.4k • 6
jordanpainter/alignment-australian-final
Viewer • Updated • 11.8k • 90
jordanpainter/dialect-preferences
Preview • Updated • 7