jvonrad/Qwen-2.5-7B-CM-Align-10k
Text Generation • Updated • 9
Jonathan von Rad
jvonrad
·
AI & ML interests
LLM Compression & Mechanistic Interpretability
Recent Activity
published a model 5 days ago
jvonrad/Qwen-2.5-7B-grpo-clip5-1500 updated a model 5 days ago
jvonrad/Qwen-2.5-7B-CM-Align-10k published a model 5 days ago
jvonrad/Qwen-2.5-7B-CM-Align-10kOrganizations
jvonrad/Qwen-2.5-7B-CPT-DCO-10k
Text Generation • Updated • 7
jvonrad/Qwen-2.5-7B-DCO-10k
Text Generation • Updated • 9
jvonrad/Qwen-2.5-7B-CPT-SFT-10k
Text Generation • Updated • 8
jvonrad/Qwen-2.5-7B-SFT-10k
Text Generation • Updated • 7
jvonrad/OLMo-2-7B-GRPO-ladder-s6500
Text Generation • Updated • 10
jvonrad/OLMo-2-7B-CM-Align-10k
Text Generation • Updated • 8
jvonrad/OLMo-2-7B-CPT-DCO-10k
Text Generation • Updated • 7
jvonrad/OLMo-2-7B-DCO-10k
Text Generation • Updated • 9
jvonrad/OLMo-2-7B-CPT-SFT-10k
Text Generation • Updated • 8
jvonrad/OLMo-2-7B-SFT-10k
Text Generation • Updated • 8
jvonrad/xscript-eval
Updated
jvonrad/Qwen-2.5-7B-grpo-clip5-1500
8B • Updated
jvonrad/Qwen-2.5-7B-grpo-bonus5-ablation
8B • Updated • 78
jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation
8B • Updated • 66
jvonrad/Qwen-2.5-CM-Align
Text Generation • 8B • Updated • 34
jvonrad/OLMo-2-7B-CM-Align
Text Generation • 7B • Updated • 47
jvonrad/Qwen-2.5-7B-SFT-CE-random
8B • Updated • 17
jvonrad/Qwen-2.5-7B-SFT-CE-fact-grouped
8B • Updated • 6
jvonrad/Qwen-2.5-7B-TED-SFT
8B • Updated • 15
jvonrad/Qwen-2.5-7B-SFT-CE
8B • Updated • 8
jvonrad/Qwen-2.5-7B-TED-grpo
Text Generation • 8B • Updated • 20
jvonrad/Qwen-2.5-7B-grpo-consistent
8B • Updated • 27
jvonrad/Qwen-2.5-7B-sft
8B • Updated • 6
jvonrad/Llama-3.1-8B-TED-grpo
Text Generation • 8B • Updated • 7
jvonrad/Llama-3.1-8B-grpo
Text Generation • 8B • Updated • 3
jvonrad/OLMo-2-7B-grpo
7B • Updated • 16
jvonrad/OLMo-2-1124-7B-TED
Text Generation • 7B • Updated • 27
jvonrad/Gemma-2-9B-TED
Text Generation • 9B • Updated • 14
jvonrad/Llama-3.1-8B-TED
8B • Updated • 7