Reasoning models trained on synthetic data using reinforcement learning.
Yichao 'Peak' Ji
peakji
AI & ML interests
Small Language Models, Retrieval-Augmented Generation, Information Extraction
Recent Activity
upvoted
a
collection
6 days ago
DeepSeek-R1
liked
a model
6 days ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
liked
a model
7 days ago
deepseek-ai/DeepSeek-R1
Organizations
Collections
3
models
14
peakji/qwen2.5-coder-7b-awq
Updated
•
4
peakji/steiner-32b-preview-gguf
Updated
•
339
•
16
peakji/steiner-32b-preview-awq
Updated
•
4
•
3
peakji/steiner-32b-preview
Updated
•
24
•
44
peakji/peak-reasoning-7b-gguf
Updated
•
255
•
4
peakji/peak-reasoning-7b-awq
Updated
•
13
peakji/peak-reasoning-7b
Updated
•
3
peakji/qwen2.5-72b-instruct-trim
Updated
•
2
peakji/qwen2.5-32b-instruct-trim
Updated
•
3
peakji/qwen2.5-14b-instruct-trim
Updated
•
4
datasets
8
peakji/peak-text-with-context-2m
Viewer
•
Updated
•
2.07M
•
126
peakji/peak-anchor-content-plain-20k
Viewer
•
Updated
•
20.1k
•
134
peakji/peak-search-content-plain-40k
Viewer
•
Updated
•
40.4k
•
99
peakji/peak-anchor-content-35k
Viewer
•
Updated
•
35.6k
•
85
peakji/peak-search-content-70k
Viewer
•
Updated
•
70.2k
•
95
peakji/peak-anchor-40k
Viewer
•
Updated
•
42.7k
•
151
peakji/peak-search-300k
Viewer
•
Updated
•
312k
•
98
peakji/peak-intent-50
Viewer
•
Updated
•
265k
•
60