This is the collection for the paper "Memorization vs. Reasoning: Updating LLMs with New Knowledge". We provide the dataset used in this paper
Aochong Oliver Li
aochongoliverli
Ernigma's profile picture
b082f689-ebc3-413d-b1f2-27bd1e86dca7's profile picture
ganglovegang's profile picture
·
AI & ML interests
Large Language Models, Natural Language Processing, Machine Learning
Recent Activity
updated
a dataset
1 day ago
aochongoliverli/Qwen2.5-1.5B-DeepMath-sft-step1400-stage1-dapo-level3-4-rollout-4-max-len-4608-rollouts
published
a dataset
1 day ago
aochongoliverli/Qwen2.5-1.5B-DeepMath-sft-step1400-stage1-dapo-level3-4-rollout-4-max-len-4608-rollouts
updated
a model
2 days ago
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1890
Organizations
None yet
models
31
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1890
2B
•
Updated
•
6
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1600
2B
•
Updated
•
10
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1400
2B
•
Updated
•
29
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1200
2B
•
Updated
•
5
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-1000
2B
•
Updated
•
5
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-800
2B
•
Updated
•
5
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-600
2B
•
Updated
•
5
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-400
2B
•
Updated
•
5
aochongoliverli/Qwen2.5-1.5B-DeepMath-level1-4-40k-all_rollouts-sft-stage0-step-200
2B
•
Updated
•
49
aochongoliverli/R1-Distill-Qwen-1.5B-DeepMath-level3-4-stage1-grpo-5epochs-4rollouts-8192max-length
2B
•
Updated
•
215
datasets
41
aochongoliverli/Qwen2.5-1.5B-DeepMath-sft-step1400-stage1-dapo-level3-4-rollout-4-max-len-4608-rollouts
Viewer
•
Updated
•
11k
•
43
aochongoliverli/DeepMath-level1-4-40k-all_rollouts-sft
Viewer
•
Updated
•
40.3k
•
17
aochongoliverli/Qwen2.5-3B-countdown-level-5-3epochs-4rollouts-8192max-length-stage2-corrupt_numbers-rollouts
Viewer
•
Updated
•
6.74k
•
141
aochongoliverli/DeepMath-level1-5-117k-all_rollouts-sft
Viewer
•
Updated
•
117k
•
27
aochongoliverli/countdown_level_6
Viewer
•
Updated
•
55k
•
229
aochongoliverli/R1-Distill-Qwen-1.5B-DeepMath-stage2-grpo-level3-4-5epochs-4rollouts-8192max-length-rollouts
Viewer
•
Updated
•
6.59k
•
113
aochongoliverli/R1-Distill-Qwen-1.5B-DeepMath-stage1-grpo-level3-4-5epochs-4rollouts-8192max-length-rollouts
Viewer
•
Updated
•
12.2k
•
200
aochongoliverli/Qwen2.5-3B-math8k-grpo-20epochs-8rollouts-8192max-length-rollouts
Viewer
•
Updated
•
8.35k
•
57
aochongoliverli/Qwen2.5-1.5B-DeepMath-stage1-grpo-level5-4epochs-4rollouts-8192max-length-rollouts
Viewer
•
Updated
•
26.6k
•
287
aochongoliverli/Qwen2.5-1.5B-DeepMath-stage1-grpo-level5-5epochs-6rollouts-16384max-length-rollouts
Viewer
•
Updated
•
11.5k
•
82