Shenzhi Wang
shenzhi-wang
AI & ML interests
Large Language Model, Reinforcement Learning, and AI Agents
Recent Activity
authored
a paper
3 days ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
commented on
a paper
4 days ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
Organizations
Collections
5
-
shenzhi-wang/Llama3-8B-Chinese-Chat
Text Generation • Updated • 9.33k • • 681 -
shenzhi-wang/Llama3-70B-Chinese-Chat
Text Generation • Updated • 53 • • 102 -
shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-8bit
Text Generation • Updated • 881 • 165 -
shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-4bit
Text Generation • Updated • 648 • 26
models
14
shenzhi-wang/Llama3.1-70B-Chinese-Chat
Text Generation
•
Updated
•
702
•
•
44
shenzhi-wang/Llama3.1-8B-Chinese-Chat
Text Generation
•
Updated
•
14.4k
•
•
262
shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-f16
Text Generation
•
Updated
•
46
•
1
shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-8bit
Text Generation
•
Updated
•
18
•
3
shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-4bit
Text Generation
•
Updated
•
78
•
2
shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
Text Generation
•
Updated
•
17
•
17
shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit
Text Generation
•
Updated
•
834
•
18
shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-f16
Text Generation
•
Updated
•
506
•
29
shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-4bit
Text Generation
•
Updated
•
648
•
26
shenzhi-wang/Llama3-8B-Chinese-Chat-GGUF-8bit
Text Generation
•
Updated
•
881
•
165
datasets
0
None public yet