dgonier/ipda-targeted-sft-v1
31B • Updated
• 21
Devin Gonier
dgonier
AI & ML interests
AI Debate, Dialectical Reasoning, LLM Research
Recent Activity
published
a dataset about 6 hours ago
dgonier/ipda-targeted-sft-v2 updated
a dataset 2 days ago
dgonier/ipda-targeted-sft-v2 liked
a model 3 days ago
Qwen/Qwen3.5-35B-A3B Organizations
dgonier/ipda-iter3-grpo-final-fp8
Text Generation • 31B • Updated
• 17
dgonier/ipda-iter3-grpo-final
31B • Updated
• 1.11k
dgonier/iter3-grpo-lora-groupD
Text Generation • Updated
• 6
dgonier/iter3-grpo-lora-groupC
Text Generation • Updated
• 7
dgonier/iter3-grpo-lora-groupB
Text Generation • Updated
• 6
dgonier/iter3-grpo-lora-groupA
Text Generation • Updated
• 6
dgonier/debate-grpo-nc-branched-groupD-epoch2
Updated
dgonier/debate-grpo-nc-branched-groupD-epoch1
Updated
dgonier/unconscious_memories_phi_weights
Updated
dgonier/debate-grpo-nc-branched-groupC-epoch2
Updated
dgonier/debate-grpo-nc-branched-groupC-epoch1
Updated
dgonier/debate-grpo-nc-branched-groupB-epoch4
Updated
dgonier/debate-grpo-nc-branched-groupB-epoch3
Updated
dgonier/debate-grpo-nc-branched-groupB-final
Updated
dgonier/debate-grpo-nc-branched-groupB-epoch2
Updated
dgonier/debate-grpo-nc-branched-groupB-epoch1
Updated
dgonier/debate-grpo-nc-branched-groupA-final
Updated
dgonier/debate-grpo-nc-branched-groupA-epoch4
Updated
dgonier/debate-grpo-nc-branched-groupA-epoch3
Updated
dgonier/debate-grpo-nc-branched-groupA-epoch2
Updated
dgonier/debate-grpo-nc-branched-groupA-epoch1
Updated
dgonier/debate-qwen-32b-iter3-grpoD
Text Generation • 31B • Updated
• 4
dgonier/debate-grpo-iter2-group-B-lora
Updated
dgonier/llama3-8b-card-cutter
Updated
• 2
dgonier/Llama-3-8B-ORPO-Debate-Card-Cutting
Text Generation • 8B • Updated
• 2
dgonier/openaccess-ai-collective-believer
Text Generation • 7B • Updated
• 2
dgonier/openaccess-ai-collective-hermes-believer
Updated