stindardlogic/tool-use-dpo-100k
Viewer • Updated • 100k • 30
Stindard Logic
stindardlogic
AI & ML interests
None yet
Organizations
None yet
stindardlogic/code-generation-sft-100k
Viewer • Updated • 100k • 103
stindardlogic/honest-uncertainty-sft-100k
Viewer • Updated • 100k • 108 • 1
stindardlogic/debate-argumentation-sft-100k
Viewer • Updated • 100k • 22
stindardlogic/instruction-following-hard-sft-100k
Viewer • Updated • 100k • 120
stindardlogic/adversarial-robustness-dpo-100k
Viewer • Updated • 100k • 35
stindardlogic/sycophancy-reduction-dpo-100k
Viewer • Updated • 100k • 33
stindardlogic/constitutional-ai-revisions-sft-100k
Viewer • Updated • 100k • 37
stindardlogic/thinking-traces-sft-100k
Viewer • Updated • 100k • 49 • 1
stindardlogic/agent-planning-sft-50k
Viewer • Updated • 50k • 207 • 18
stindardlogic/customer-service-sft-50k
Viewer • Updated • 50k • 99
stindardlogic/creative-writing-sft-50k
Viewer • Updated • 50k • 4.86k
stindardlogic/hallucination-reduction-dpo-100k
Viewer • Updated • 100k • 48
stindardlogic/summarization-sft-100k
Preview • Updated • 27
stindardlogic/code-debugging-sft-50k
Viewer • Updated • 50k • 173
stindardlogic/writing-quality-dpo-100k
Viewer • Updated • 100k • 620 • 1
stindardlogic/science-qa-sft-100k
Viewer • Updated • 100k • 82
stindardlogic/instruction-following-dpo-100k
Viewer • Updated • 100k • 111 • 3
stindardlogic/tool-calling-english-100k
Viewer • Updated • 100k • 233 • 2
stindardlogic/math-reasoning-sft-100k
Viewer • Updated • 100k • 79 • 1
stindardlogic/system-prompt-sft-50k
Viewer • Updated • 50k • 53 • 2
stindardlogic/preference-pairs-coding-50k
Viewer • Updated • 50k • 20
stindardlogic/multi-turn-chat-sft-50k
Viewer • Updated • 50k • 46 • 1
stindardlogic/llm-judge-dpo-5k
Viewer • Updated • 5k • 29
stindardlogic/dpo-general-helpfulness-15k
Viewer • Updated • 15k • 23
stindardlogic/prompt-injection-defense-dpo-3k
Viewer • Updated • 3k • 41
stindardlogic/instruct-sft-alpaca-20k
Viewer • Updated • 20k • 45
stindardlogic/json-structured-output-dpo-3k
Viewer • Updated • 3k • 22
stindardlogic/rag-grounding-dpo-4k
Viewer • Updated • 4k • 15
stindardlogic/code-review-dpo-3k
Viewer • Updated • 3k • 50