Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-switch-top1-router-ffn-lora-aux-anneal-5ep
Updated
Jongbin Won
Jongbin-kr
AI & ML interests
None yet
Recent Activity
updated a model about 7 hours ago
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-lbox-switch-top1-router-ffn-lora-aux-anneal-5ep updated a model about 8 hours ago
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-switch-top1-router-ffn-lora-aux-anneal-5ep published a model about 17 hours ago
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-switch-top1-router-ffn-lora-aux-anneal-5epOrganizations
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-lbox-switch-top1-router-ffn-lora-aux-anneal-5ep
Updated
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-switch-top1-router-ffn-lora-sft-5ep
Text Generation • Updated
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-lbox-switch-top1-router-ffn-lora-sft-5ep
Updated • 1
Jongbin-kr/exaone-3.5-7.8b-verireason-full-ft-reasoning-co-ratio1.0-epoch3
Text Generation • 8B • Updated • 303
Jongbin-kr/exaone-7b-verireason-reproduced-1513-fullft-best-grpo-reproduced-1.0
Updated
Jongbin-kr/exaone-3.5-7.8b-verireason_full-ft_sft-original-1.0_grpo-reproduced-1.0
8B • Updated • 9
Jongbin-kr/exaone-3.5-7.8b-verireason_full-ft_sft-original-1.0_grpo-original-1.0
8B • Updated • 19
Jongbin-kr/exaone-3.5-7.8b-verireason-reproduced-1513-sft-best-full-grpo-qwen-optim-exaone-sampling
Updated
Jongbin-kr/exaone-3.5-7.8b-verireason-sft-best-full-grpo-qwen-optim-exaone-sampling
Updated
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-router-ffn-lora-sft-5ep
Updated • 2
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-switch-top1
Text Generation • 25B • Updated • 415 • 2
Jongbin-kr/exaone-3.5-7.8b-verireason-sft-best-full-grpo-qwen-matched
Updated
Jongbin-kr/exaone-3.5-7.8b-verireason-sft-best-e1-full-grpo-ratio1.0-epoch1
Updated
Jongbin-kr/llama-3.1-8b-instruct_LBox-10x2-clustered-fallback-plus-shared-lora-moe
Updated
Jongbin-kr/qwen2.5-coder-7b-verireason-grpo-official-full-ft
Text Generation • 8B • Updated • 2.57k
Jongbin-kr/exaone-7b-verireason-reproduced-1513-fullft-epoch4
Text Generation • 8B • Updated • 478
Jongbin-kr/llama-3.1-8b-instruct_LBox-10x2-fallback-plus-generalist-lora-moe
Updated
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-lbox-ffn-lora-sft-5ep-checkpoint-4200
Updated
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-ffn-lora-checkpoint-4000
Text Generation • Updated • 13
Jongbin-kr/llama-3.1-8b-instruct-4x1-moe-sni-ffn-lora
Updated • 59
Jongbin-kr/qwen2.5-coder-7b-verireason-grpo-custom-sft-1.0
Text Generation • Updated • 21
Jongbin-kr/llama-3.1-8b-instruct_LBox-task-prior-3x1-lora-moe
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-shared-generalist_fallback_ffn-only
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-criminal-charge-aggregator_fallback_ffn-only
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-legal-recidivism-analyst_fallback_ffn-only
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-judicial-labeling-precisionist_fallback_ffn-only
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-civil-dispute-taxonomy-expert_fallback_ffn-only
Updated
Jongbin-kr/llama-3.1-8b-instruct_SNI-ours-16x2-plus-generalist-lora-moe
Updated
Jongbin-kr/llama-3.1-8b-instruct_lbox-legal-provision-auditor_fallback_ffn-only
Updated