HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k
Text Generation • 16B • Updated • 255 • 2
Haoze He
HectorHe
AI & ML interests
LLMSys, LLM, MLSys
Recent Activity
published a model 2 days ago
HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Fix-Expert-Dense-32-experts liked a model 5 days ago
HectorHe/DeepSeek-V2-Lite-aux-free-sft-math7k-1epoch-1e-4-gamma liked a model 6 months ago
HectorHe/DeepSeek-V2-Lite-aux-free-sft-commonsense-1epoch-1e-5-gamma-share-expertOrganizations
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-sft-math14k
Text Generation • 16B • Updated • 3 • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-sft-s1K
Text Generation • 16B • Updated • 11 • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-sft-nemotron-code
Text Generation • 126k • Updated • 7 • 1
HectorHe/OLMoE-1B-7B-0125-sft-math14k
Text Generation • 7B • Updated • 3 • 1
HectorHe/Qwen1.5-MOE-sft-nemotron-code
Text Generation • 14B • Updated • 3 • 1
HectorHe/OLMoE-1B-7B-0125-sft-nemotron-code
Text Generation • 133k • Updated • 4 • 1
HectorHe/GPT-oss-sft-s1K
Text Generation • 4.76M • Updated • 7 • 1
HectorHe/OLMoE-1B-7B-0125-sft-s1K
Text Generation • 133k • Updated • 6 • 1
HectorHe/OLMoE-1B-7B-0125-sft-math7k
Text Generation • 7B • Updated • 4 • 1
HectorHe/gpt-oss-20b-math7k
Text Generation • 4.76M • Updated • 5 • 1
HectorHe/Qwen1.5-MOE-sft-s1K
Text Generation • 14B • Updated • 7 • 1
HectorHe/Qwen1.5-MOE-sft-math14k
Text Generation • 14B • Updated • 7 • 3
HectorHe/Qwen1.5-MOE-sft-math7k
Text Generation • 14B • Updated • 6 • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-mixture-new
16B • Updated • 2
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-forward-kl-new
16B • Updated • 2
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-test-may
3B • Updated • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-mixture
16B • Updated • 2
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-forward-kl
16B • Updated • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-token-specific
16B • Updated • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-token-specific-scale
16B • Updated • 5
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-test-new-module
Updated
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-token-specific
3B • Updated • 1
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-token-specific-3-scaled
3B • Updated • 2
HectorHe/Qwen2.5-1.5B-Open-R1-Distill-3-epoch
Text Generation • 2B • Updated • 4
HectorHe/Qwen2.5-1.5B-Open-R1-Distill-run2
2B • Updated
HectorHe/Qwen2.5-1.5B-Open-R1-Distill
Text Generation • 2B • Updated • 5
HectorHe/Qwen3-8B-math220k-run7
Text Generation • 8B • Updated • 3
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-test-token-specific-5-epoch
3B • Updated • 2
HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-Distill-6-experts-test-token-specific
3B • Updated • 2