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
google/siglip2-so400m-patch14-384
liked
a model
7 days ago
nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base
liked
a model
12 days ago
google/gemma-3-4b-pt
Organizations
models
14
peakji/qwen2.5-coder-7b-awq
2B
•
Updated
•
1.12k
peakji/steiner-32b-preview-gguf
33B
•
Updated
•
17
•
23
peakji/steiner-32b-preview-awq
6B
•
Updated
•
3
•
4
peakji/steiner-32b-preview
33B
•
Updated
•
3
•
92
peakji/peak-reasoning-7b-gguf
8B
•
Updated
•
15
•
4
peakji/peak-reasoning-7b-awq
2B
•
Updated
•
3
peakji/peak-reasoning-7b
8B
•
Updated
•
4
peakji/qwen2.5-72b-instruct-trim
73B
•
Updated
•
4
peakji/qwen2.5-32b-instruct-trim
33B
•
Updated
•
5
peakji/qwen2.5-14b-instruct-trim
15B
•
Updated
•
5
datasets
8
peakji/peak-text-with-context-2m
Viewer
•
Updated
•
2.07M
•
190
peakji/peak-anchor-content-plain-20k
Viewer
•
Updated
•
20.1k
•
15
peakji/peak-search-content-plain-40k
Viewer
•
Updated
•
40.4k
•
38
peakji/peak-anchor-content-35k
Viewer
•
Updated
•
35.6k
•
40
peakji/peak-search-content-70k
Viewer
•
Updated
•
70.2k
•
20
peakji/peak-anchor-40k
Viewer
•
Updated
•
42.7k
•
16
peakji/peak-search-300k
Viewer
•
Updated
•
312k
•
31
peakji/peak-intent-50
Viewer
•
Updated
•
265k
•
4