LM Playschool Challenge Our series of models trained for the beta version of the challenge (sorted by performance) pm-25/llama3-8b-sft Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-grpo Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-sft-initial Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-sft-grpo Text Generation • 8B • Updated Sep 15, 2025
LM Playschool Challenge Our series of models trained for the beta version of the challenge (sorted by performance) pm-25/llama3-8b-sft Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-grpo Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-sft-initial Text Generation • Updated Sep 27, 2025 pm-25/llama3-8b-sft-grpo Text Generation • 8B • Updated Sep 15, 2025
