Jiayu (Mila) Wang
MilaWang
AI & ML interests
Large Language Model, Multimodal Large Language Model, Agentic System, Reasoning, Efficiency
Recent Activity
updated
a model
6 days ago
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step880
published
a model
6 days ago
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step880
updated
a model
6 days ago
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step800
Organizations
models and datasets used in the SparkleRL&SPARKLE project
-
sparkle-reasoning/sparkle_preview
Viewer • Updated • 18k • 41 • 1 -
sparkle-reasoning/SparkleRL-7B-Stage2-aug
Reinforcement Learning • 8B • Updated • 13 • 3 -
sparkle-reasoning/SparkleRL-7B-Stage2-mix
Text Generation • 8B • Updated • 10 -
sparkle-reasoning/SparkleRL-7B-Stage2-hard
Text Generation • 8B • Updated • 13
models and datasets used in the SparkleRL&SPARKLE project
-
sparkle-reasoning/sparkle_preview
Viewer • Updated • 18k • 41 • 1 -
sparkle-reasoning/SparkleRL-7B-Stage2-aug
Reinforcement Learning • 8B • Updated • 13 • 3 -
sparkle-reasoning/SparkleRL-7B-Stage2-mix
Text Generation • 8B • Updated • 10 -
sparkle-reasoning/SparkleRL-7B-Stage2-hard
Text Generation • 8B • Updated • 13
models
40
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step880
8B
•
Updated
•
13
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step800
8B
•
Updated
•
7
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step720
8B
•
Updated
•
9
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step640
8B
•
Updated
•
8
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step560
8B
•
Updated
•
10
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step480
8B
•
Updated
•
8
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step400
8B
•
Updated
•
8
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step320
8B
•
Updated
•
5
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step240
8B
•
Updated
•
8
MilaWang/es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step160
8B
•
Updated
•
7
datasets
206
MilaWang/qa_validation_qwen
Viewer
•
Updated
•
700
•
116
MilaWang/qa_test_qwen
Viewer
•
Updated
•
4.26k
•
98
MilaWang/qa-dataset-qwen
Viewer
•
Updated
•
14.2k
•
12
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-16-shots-sd4
Viewer
•
Updated
•
2.85k
•
13
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-8-shots-sd4
Viewer
•
Updated
•
2.85k
•
13
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-4-shots-sd4
Viewer
•
Updated
•
2.85k
•
14
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-2-shots-sd4
Viewer
•
Updated
•
2.85k
•
8
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-1-shots-sd4
Viewer
•
Updated
•
2.85k
•
16
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-16-shots-sd3
Viewer
•
Updated
•
2.85k
•
13
MilaWang/mmlu-routerbench-0shot-contrast-full-by-task-dense-8-shots-sd3
Viewer
•
Updated
•
2.85k
•
10