AI & ML interests
None yet
Organizations
None yet
models 42
akbarsigit/llama3.1-grpo-r256-a512-base-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-grpo-r256-a512-base-lora
Updated
akbarsigit/llama3.1-grpo-r256-a512-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-grpo-r256-a512-lora
Updated
akbarsigit/llama3.1-grpo-r128-a256-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-grpo-r128-a256-lora
Updated
akbarsigit/llama3.1-grpo-r64-a128-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-grpo-r64-a128-lora
Updated
akbarsigit/llama3.1-kto-r64-a128-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-kto-r64-a128-lora
Updated