Top LLMs 2025: ZAI GLM-4.7 (358B) & Moonshot Kimi-K2-Thinking. Next-gen reasoning, code, multilingual. State-of-the-art performance. Production-ready.
Karsten Kuhnke PRO
mindchain
AI & ML interests
Mechanistic Interpretability, Sparse Autoencoders, JumpReLU, Reward Modeling, RLHF, AI Alignment, Function Calling, Gemma, Nemotron
Recent Activity
updated
a model
about 2 hours ago
mindchain/qwen3-0.6b-dpo
updated
a Space
about 3 hours ago
mindchain/trackio
published
a Space
about 3 hours ago
mindchain/trackio
Organizations
models
43
mindchain/qwen3-0.6b-dpo
Updated
mindchain/colab-sft-trainer
Updated
mindchain/functiongemma-270m-sae
Updated
mindchain/t5gemma2-sae-all-layers
Updated
•
1
mindchain/haddock_reward_mini
8B
•
Updated
•
5
mindchain/Llama-3-8B-AWQ-4bit
Updated
mindchain/qwen1.5-llm
Updated
mindchain/merged-quantized-phi-3-mini-4k
Text Generation
•
4B
•
Updated
•
6
mindchain/gguf-quantized-phi-3-mini-4k
Updated
mindchain/gedapter1
Updated
datasets
35
mindchain/mobile-actions
Viewer
•
Updated
•
9.65k
•
7
mindchain/my-distiset-63420a29
Viewer
•
Updated
•
10
•
9
mindchain/synthetic_agri_dataset
Viewer
•
Updated
•
1k
•
24
mindchain/wikitext2
Updated
•
163
•
6
mindchain/orca_02
Viewer
•
Updated
•
3
•
15
mindchain/ORCA_GOT_STYLE
Viewer
•
Updated
•
1
•
47
•
1
mindchain/bush_01
Viewer
•
Updated
•
1
•
20
mindchain/demo_25
Viewer
•
Updated
•
60
•
65
mindchain/demo_24
Viewer
•
Updated
•
60
•
42
mindchain/demo_23
Preview
•
Updated
•
15