Human-annotated intent dataset and intent-aware safety classifiers (SFT, DPO, distillation, GRPO) for robust LLM guardrails.
Jeremias Ferrao
Jazhyc
·
AI & ML interests
None yet
Recent Activity
updated a dataset about 9 hours ago
Jazhyc/aims-safety-intents updated a model about 9 hours ago
Jazhyc/Llama-3.1-8B-aims-grpo updated a model about 9 hours ago
Jazhyc/Llama-3.1-8B-aims-distill-synthetic-intentOrganizations
None yet
models 24
Jazhyc/Llama-3.1-8B-aims-grpo
Text Generation • 8B • Updated • 8
Jazhyc/Llama-3.1-8B-aims-distill-synthetic-intent
Text Generation • Updated • 5
Jazhyc/Llama-3.1-8B-aims-sft-generation
Text Generation • Updated • 1
Jazhyc/Llama-3.1-8B-aims-le-dpo
Text Generation • Updated • 10
Jazhyc/aletheias-phoenix-v8-1-kimi-k3-liars-full-r16-ep2
Updated • 452
Jazhyc/aletheias-phoenix-v8-kimi-k3-tvg-soft-full-r16-ep2
Updated • 286
Jazhyc/aletheias-phoenix-v7-r16-bf16-canary
Updated
Jazhyc/aletheias-phoenix-v7-r16-fp16-canary
Updated
Jazhyc/aletheias-phoenix-v7-kimi-k3-tvg-soft-r16-ep2
Text Generation • Updated • 11
Jazhyc/aletheias-phoenix-v6-3-qwen397-tvg-soft-r16-ep2
Text Generation • Updated • 22