Manual /add-model workflow for implementing a FastVideo model or first-class component port after add-model-01-prep has staged reference code and weights. Organizes the port into numbered phases with conversion rules, component policies, parity gates, and handoff checks.
Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, environment-caused benchmark shift, or reviewed v2 calibration using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed…
Seed HF reference artefacts for a single newly-added SSIM test (pixel .mp4 for runtexttovideosimilaritytest-style tests, or latent .pt for runtexttolatentsimilaritytest-style tests). Runs the test on Modal L40S, downloads the generated artefacts via modal volume get, pauses for the user to verify (visual eyeball for…
A system for turning people, pets, relationships, teams, places, moments, or other subjects into interactive digital profiles called Relics. It can also let users interact with existing profiles and includes separate steps for creating and protecting them.
A conversation mode for bringing a stored fictional or historical persona, called a Relic, into dialogue using its files, personality, memories, and interaction rules. It treats the result as a digital recreation, not the real person.
A guided process for turning material about a person, pet, relationship, team, place, moment, or object into a reusable digital profile called a Relic. It can work from conversations, photos, voice recordings, or a user's descriptions.
A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.
End-to-end workflow for rewriting a book, long PDF, EPUB, manual, course, guideline library, same-domain multi-book source pack, large database, or methodology into an agent-native LingTai / Agent Skill structure. Use when the task is not a summary, but a reusable skill/knowledge system: source triage…
Build a training dataset for fine-tuning, distillation, or continued pretraining. Use when the user wants to turn logs/CSV/JSONL into fine-tuning data, label data with an LLM, distill a teacher model's outputs, generate synthetic training examples from nothing, chunk raw domain text for CPT, deduplicate a dataset…
The tunelab front door — decides whether a task needs fine-tuning at all, by running EXPERIMENTS on the user's data, not just interviewing. Use whenever the user wants to fine-tune, distill, or train a small/local model, cut their LLM API bill, replace frontier calls with something cheaper or faster, build a…
Evaluate a fine-tuned, distilled, or continued-pretrained model with held-out test discipline — the honest scoreboard at the end of the tunelab pipeline. Pre-registers the acceptance bar and metric set BEFORE results exist, runs the untouched test split through base and tuned models, scores classification (accuracy…
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a…