Our series of models trained for the beta version of the challenge (sorted by performance)
AI & ML interests
None defined yet.
models
7
pm-25/llama3-8b-dpo_clean
Text Generation
•
Updated
pm-25/llama3-8b-grpo
Text Generation
•
Updated
pm-25/llama3-8b-sft-initial
Text Generation
•
Updated
pm-25/llama3-8b-sft
Text Generation
•
Updated
pm-25/llama3-8b-sft-grpo
Text Generation
•
8B
•
Updated
•
2
pm-25/llama3-8b-sft-dpo-tulu-only
Text Generation
•
8B
•
Updated
•
1
pm-25/llama3-8b-sft-dpo
Text Generation
•
8B
•
Updated
•
1