Reasoning models trained on synthetic data using reinforcement learning.
Yichao 'Peak' Ji
peakji
AI & ML interests
Agents, Small Language Models, Retrieval-Augmented Generation, Information Extraction
Recent Activity
liked
a model
about 1 month ago
sand-ai/MAGI-1
liked
a model
2 months ago
Qwen/Qwen2.5-VL-32B-Instruct
liked
a dataset
2 months ago
starvector/text2svg-stack
Organizations
Collections
3
models
14
peakji/qwen2.5-coder-7b-awq
Updated
•
433
peakji/steiner-32b-preview-gguf
Updated
•
85
•
22
peakji/steiner-32b-preview-awq
Updated
•
5
•
4
peakji/steiner-32b-preview
Updated
•
10
•
93
peakji/peak-reasoning-7b-gguf
Updated
•
145
•
4
peakji/peak-reasoning-7b-awq
Updated
•
8
peakji/peak-reasoning-7b
Updated
•
8
peakji/qwen2.5-72b-instruct-trim
Updated
•
3
peakji/qwen2.5-32b-instruct-trim
Updated
•
5
peakji/qwen2.5-14b-instruct-trim
Updated
•
2
datasets
8
peakji/peak-text-with-context-2m
Viewer
•
Updated
•
2.07M
•
239
peakji/peak-anchor-content-plain-20k
Viewer
•
Updated
•
20.1k
•
189
peakji/peak-search-content-plain-40k
Viewer
•
Updated
•
40.4k
•
206
peakji/peak-anchor-content-35k
Viewer
•
Updated
•
35.6k
•
196
peakji/peak-search-content-70k
Viewer
•
Updated
•
70.2k
•
149
peakji/peak-anchor-40k
Viewer
•
Updated
•
42.7k
•
235
peakji/peak-search-300k
Viewer
•
Updated
•
312k
•
185
peakji/peak-intent-50
Viewer
•
Updated
•
265k
•
107