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
2 days ago
Qwen/QwQ-32B
upvoted
a
collection
25 days ago
🧠 Reasoning datasets
Organizations
Collections
3
models
14

peakji/qwen2.5-coder-7b-awq
Updated
•
101

peakji/steiner-32b-preview-gguf
Updated
•
107
•
18

peakji/steiner-32b-preview-awq
Updated
•
11
•
3

peakji/steiner-32b-preview
Updated
•
19
•
44

peakji/peak-reasoning-7b-gguf
Updated
•
376
•
4

peakji/peak-reasoning-7b-awq
Updated
•
11

peakji/peak-reasoning-7b
Updated
•
19

peakji/qwen2.5-72b-instruct-trim
Updated
•
3

peakji/qwen2.5-32b-instruct-trim
Updated
•
3

peakji/qwen2.5-14b-instruct-trim
Updated
•
12
datasets
8
peakji/peak-text-with-context-2m
Viewer
•
Updated
•
2.07M
•
235
peakji/peak-anchor-content-plain-20k
Viewer
•
Updated
•
20.1k
•
833
peakji/peak-search-content-plain-40k
Viewer
•
Updated
•
40.4k
•
272
peakji/peak-anchor-content-35k
Viewer
•
Updated
•
35.6k
•
454
peakji/peak-search-content-70k
Viewer
•
Updated
•
70.2k
•
239
peakji/peak-anchor-40k
Viewer
•
Updated
•
42.7k
•
297
peakji/peak-search-300k
Viewer
•
Updated
•
312k
•
312
peakji/peak-intent-50
Viewer
•
Updated
•
265k
•
254