avocet

research: evaluate HRM-Text-1B as fine-tuning base for email classifier

#68 opened 2026-05-22 19:47:43 -07:00 by pyr0ball

Rename CF_ORCH_URL to GPU_SERVER_URL for self-hoster clarity

#66 opened 2026-05-17 09:36:04 -07:00 by pyr0ball

feat: fleet tab — download from public source or rsync to node when model is missing

#64 opened 2026-05-13 08:29:58 -07:00 by pyr0ball

feat: Assignments tab on fleet page — manage product.task → model routing

#63 opened 2026-05-13 08:21:19 -07:00 by pyr0ball

Integrate task-model assignment routing for imitate inference via cf-orch /api/inference/task

#62 opened 2026-05-13 07:38:23 -07:00 by pyr0ball 0 / 3

feat: log corpus receiver — accept Turnstone push batches, label for logreading fine-tune

#61 opened 2026-05-11 16:17:47 -07:00 by pyr0ball

cf-a11y review: EmbedCompareTab.vue (avocet#59)

#60 opened 2026-05-11 08:18:27 -07:00 by pyr0ball

Embedding model comparison harness

#59 opened 2026-05-06 08:21:54 -07:00 by pyr0ball

manage.sh: add status and logs commands

#58 opened 2026-05-05 20:44:13 -07:00 by pyr0ball

Model catalogue: extend to cover Ollama embedding models alongside HuggingFace models

#57 opened 2026-05-05 14:46:27 -07:00 by pyr0ball

Add embedding model and RAG classifier support to benchmark/finetune harness

backlog

enhancement

ml

#55 opened 2026-05-04 16:13:16 -07:00 by pyr0ball 0 / 5

feat: cf-orch dispatch for training jobs (Phase 3)

backend

phase-3

#54 opened 2026-05-01 12:13:46 -07:00 by pyr0ball v2 — Pipeline Architecture

feat: voice/TTS finetuning backend (Phase 2)

backend

ml

phase-2

#53 opened 2026-05-01 12:13:46 -07:00 by pyr0ball v2 — Pipeline Architecture

feat: writing style finetuning backend (Phase 2)

backend

ml

phase-2

#52 opened 2026-05-01 12:13:45 -07:00 by pyr0ball v2 — Pipeline Architecture

EEG epoch labeling pipeline — Phase C Merlin training data

#41 opened 2026-04-26 21:47:47 -07:00 by pyr0ball

Merlin pipeline adapter — gesture/landmark labeled training data

#40 opened 2026-04-26 21:45:10 -07:00 by pyr0ball

voice benchmark: parallel model scoring to fan out across cluster nodes

#39 opened 2026-04-22 10:44:31 -07:00 by pyr0ball

feat: anonymized repair engagement corpus pipeline for Avocet fine-tuning

#38 opened 2026-04-22 10:02:10 -07:00 by pyr0ball

feat: fine-tune pipeline for writing voice model

#37 opened 2026-04-22 07:06:45 -07:00 by pyr0ball

feat: writing style benchmark harness for local text-gen models

#36 opened 2026-04-22 07:06:45 -07:00 by pyr0ball

Labels Milestones