Simon Yu

simonycl's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset 2 days ago

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-judge-mtbench_cot_helpsteer_complexity

Viewer • Updated 2 days ago • 62k • 18

updated 2 models 4 days ago

simonycl/temp_file_1

Updated 4 days ago

simonycl/llama-3-8b-instruct-agg-judge

Text Generation • Updated 4 days ago • 65

updated 5 datasets 6 days ago

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-judge-mtbench_cot_helpsteer_verbose

Viewer • Updated 6 days ago • 62k • 14

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-judge-mtbench_cot_helpsteer_helpfulness

Viewer • Updated 6 days ago • 62k • 14

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-judge-mtbench_cot_helpsteer_correctness

Viewer • Updated 6 days ago • 62k • 13

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-judge-mtbench_cot_helpsteer_coherence

Viewer • Updated 6 days ago • 62k • 21

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-Meta-Llama-3-8B-Instruct-annotate-start-0-end-1.0-judge-5

Viewer • Updated 6 days ago • 62k • 15

updated a dataset 7 days ago

simonycl/Meta-Llama-3-8B-Instruct_ultrafeedback-annotate-start-0-end-1.0-judge-5

Viewer • Updated 7 days ago • 60k • 13

updated 2 models 9 days ago

edinlp/qwen2-7b-offline-dpo

Updated 9 days ago • 6

edinlp/llama-3-8b-offline-dpo

Updated 9 days ago • 9

updated 2 models about 1 month ago

edinlp/mistral-7b-v0.3-dpo

Text Generation • Updated Oct 12 • 9

edinlp/mistral-7b-v0.3-sft

Text Generation • Updated Oct 11 • 8

updated 4 models about 2 months ago

simonycl/Tulu-2-7B-Helpful

Updated Oct 10

simonycl/Tulu-2-7B-Harmless

Updated Oct 10

simonycl/self-seq-Meta-Llama-3-8B-metamath-tulu-base-regen

Updated Oct 10 • 3

simonycl/self-seq-Meta-Llama-3-8B-metamath-tulu_seq

Updated Oct 9 • 1

updated 2 datasets about 2 months ago

simonycl/metamath-tulu-base-regen

Viewer • Updated Oct 8 • 120k • 32

simonycl/metamath-tulu-seq

Viewer • Updated Oct 8 • 120k • 33

updated a model about 2 months ago

simonycl/Llama-3-8B-DPO-Iter5

Updated Oct 2