These are the top models I developed on the open Ko-llm leaderboard.
Seungyoo Lee
DopeorNope
AI & ML interests
LLM,
Data efficiency learning,
Multi-Modal
Recent Activity
updated a model about 3 hours ago
DopeorNope/ToolWeaver-Llama-3-8B-Tool-Retriever-no-vocab published a dataset about 3 hours ago
DopeorNope/DPO-Ko-Dataset published a model about 3 hours ago
DopeorNope/ToolWeaver-Llama-3-8B-Tool-Retriever-no-vocabOrganizations
It is a collection of papers that are useful in studying LLM.
-
Attention Is All You Need
Paper • 1706.03762 • Published • 117 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 60 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 64 -
Lost in the Middle: How Language Models Use Long Contexts
Paper • 2307.03172 • Published • 44
These are the top models I developed on the open Ko-llm leaderboard.
It is a collection of papers that are useful in studying LLM.
-
Attention Is All You Need
Paper • 1706.03762 • Published • 117 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 60 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 64 -
Lost in the Middle: How Language Models Use Long Contexts
Paper • 2307.03172 • Published • 44
models 121
DopeorNope/ToolWeaver-Llama-3-8B-Tool-Retriever-no-vocab
8B • Updated
DopeorNope/ToolWeaver-Llama-3-8B-Tool-Memorization-no-vocab
8B • Updated
DopeorNope/FFT_after_init_kl_healing_kor_100
Updated
DopeorNope/FFT_after_init_only_kor
Text Generation • 8B • Updated • 5
DopeorNope/FFT_after_init_fft_healing_kor
Text Generation • 8B • Updated • 1
DopeorNope/FFT_naive_kor
Text Generation • 8B • Updated • 2
DopeorNope/FFT_after_init_fft_kor
Text Generation • 8B • Updated • 2
DopeorNope/afterFFT_and_exponent_init_trained
Text Generation • 8B • Updated • 1
DopeorNope/expanded-exponent-init-Baseline
Text Generation • 8B • Updated • 1
DopeorNope/FFT-expanded-exponent-init
Text Generation • 8B • Updated • 3
datasets 230
DopeorNope/AI_hello
Viewer • Updated • 4.65k • 21
DopeorNope/MMLU-Pro
Viewer • Updated • 12.1k • 21
DopeorNope/minif2f_test_FFT-healing-kl-ours
Viewer • Updated • 488 • 12
DopeorNope/qwen3-4b_solver_v4
Viewer • Updated • 2.9k • 14
DopeorNope/math_distilled_sequence_data
Viewer • Updated • 113k • 8
DopeorNope/qwen3-4b_solver_v3
Viewer • Updated • 3.19k • 4
DopeorNope/qwen3-4b_solver_v1
Viewer • Updated • 2.77k • 3
DopeorNope/qwen3-4b_solver_v2
Viewer • Updated • 3.36k • 11
DopeorNope/minif2f_test_fft_expanded_exponent_init
Viewer • Updated • 244 • 7
DopeorNope/minif2f_test_expanded_exponent_init_baseline
Viewer • Updated • 244 • 5