-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 85 -
SlimPajama-DC: Understanding Data Combinations for LLM Training
Paper • 2309.10818 • Published • 11 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 24 -
Contrastive Decoding Improves Reasoning in Large Language Models
Paper • 2309.09117 • Published • 40
Lei Wang
demolei
AI & ML interests
LLMs
Recent Activity
upvoted a paper about 5 hours ago
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models upvoted a paper 1 day ago
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning upvoted a paper 2 days ago
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM AgentsOrganizations
-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 85 -
SlimPajama-DC: Understanding Data Combinations for LLM Training
Paper • 2309.10818 • Published • 11 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 24 -
Contrastive Decoding Improves Reasoning in Large Language Models
Paper • 2309.09117 • Published • 40
models 6
demolei/qwen2_5_vl_7b_grpo_chartqa_filtered_40
8B • Updated
demolei/Qwen2.5-VL-7B-Instruct-chartqa_filtered_240
8B • Updated
demolei/Qwen2.5-1.5B-Open-R1-Distill
Text Generation • 2B • Updated
demolei/Qwen-2.5-7B-Simple-RL
Text Generation • 8B • Updated
demolei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
demolei/sft_openassistant-guanaco
Updated
datasets 0
None public yet