·
AI & ML interests
None yet
Organizations
None yet
zisisbatzos/GRPO_3SFTs_synthetic_emobench_llama3.2-3B
3B • Updated • 1
zisisbatzos/3SFTs_synthetic_emobench_llama3.2-3B
3B • Updated • 1
zisisbatzos/2SFTs_llama3.2-3B
Text Generation
• 3B • Updated • 2
zisisbatzos/GRPO_2SFTs_llama3.2-3B
Text Generation
• 3B • Updated • 1
zisisbatzos/GRPO_3SFTs_llama3.2-3B
Text Generation
• 3B • Updated • 1
zisisbatzos/3SFTs_llama3.2-3B
Text Generation
• 3B • Updated • 2
zisisbatzos/Llama-3.2-1B-Instruct-GRPO
Text Generation
• 1B • Updated • 3
• zisisbatzos/llama3.2-1B-GRPO
Text Generation
• 1B • Updated • 5
• zisisbatzos/emollama-3.1-8B-lr-1e-5
Text Generation
• 8B • Updated • 3
zisisbatzos/emollama-3.1-8B-r-256
Text Generation
• 8B • Updated • 2
zisisbatzos/emollama-3.1-8B-r-128
Text Generation
• 8B • Updated • 2
zisisbatzos/emollama-3.1-8B-r-64
Text Generation
• 8B • Updated • 3
zisisbatzos/emollama-3.1-8B-no-packing
Text Generation
• 8B • Updated • 2
zisisbatzos/emollama-3.1-8B-QAonly
Text Generation
• 8B • Updated • 4
zisisbatzos/baseline_llama-3.1-8B
Text Generation
• 8B • Updated • 4