jvonrad/xscript-eval
Updated
Jonathan von Rad
jvonrad
·
AI & ML interests
LLM Compression & Mechanistic Interpretability
Recent Activity
updated a model 5 days ago
jvonrad/xscript-eval updated a dataset 5 days ago
jvonrad/xscript-shards published a dataset 5 days ago
jvonrad/xscript-shardsOrganizations
jvonrad/Qwen-2.5-7B-CM-Align-10k
Text Generation • Updated • 11
jvonrad/Qwen-2.5-7B-CPT-DCO-10k
Text Generation • Updated • 9
jvonrad/Qwen-2.5-7B-DCO-10k
Text Generation • Updated • 10
jvonrad/Qwen-2.5-7B-CPT-SFT-10k
Text Generation • Updated • 8
jvonrad/Qwen-2.5-7B-SFT-10k
Text Generation • Updated • 12
jvonrad/OLMo-2-7B-GRPO-ladder-s6500
Text Generation • Updated • 11
jvonrad/OLMo-2-7B-CM-Align-10k
Text Generation • Updated • 10
jvonrad/OLMo-2-7B-CPT-DCO-10k
Text Generation • Updated • 8
jvonrad/OLMo-2-7B-DCO-10k
Text Generation • Updated • 10
jvonrad/OLMo-2-7B-CPT-SFT-10k
Text Generation • Updated • 9
jvonrad/OLMo-2-7B-SFT-10k
Text Generation • Updated • 12
jvonrad/Qwen-2.5-7B-grpo-clip5-1500
8B • Updated • 5
jvonrad/Qwen-2.5-7B-grpo-bonus5-ablation
8B • Updated • 8
jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation
8B • Updated • 5
jvonrad/Qwen-2.5-CM-Align
Text Generation • 8B • Updated • 18
jvonrad/OLMo-2-7B-CM-Align
Text Generation • 7B • Updated • 12
jvonrad/Qwen-2.5-7B-SFT-CE-random
8B • Updated • 3
jvonrad/Qwen-2.5-7B-SFT-CE-fact-grouped
8B • Updated • 3
jvonrad/Qwen-2.5-7B-TED-SFT
8B • Updated • 4
jvonrad/Qwen-2.5-7B-SFT-CE
8B • Updated • 3
jvonrad/Qwen-2.5-7B-TED-grpo
Text Generation • 8B • Updated • 11
jvonrad/Qwen-2.5-7B-grpo-consistent
8B • Updated • 6
jvonrad/Qwen-2.5-7B-sft
8B • Updated • 2
jvonrad/Llama-3.1-8B-TED-grpo
Text Generation • 8B • Updated • 5
jvonrad/Llama-3.1-8B-grpo
Text Generation • 8B • Updated • 4
jvonrad/OLMo-2-7B-grpo
7B • Updated • 2
jvonrad/OLMo-2-1124-7B-TED
Text Generation • 7B • Updated • 12
jvonrad/Gemma-2-9B-TED
Text Generation • 9B • Updated • 12
jvonrad/Llama-3.1-8B-TED
8B • Updated • 6