Second pre-alpha from Tyness Train, an agent-guided fine-tuning harness for small LLMs on low-VRAM GPUs. This model is RAG-style grounded: every prompt carries excerpts of the relevant norm, and the model is trained to answer only from that context. Three iterations established that SFT alone teaches format, not facts on 1.2B models: legalize-es, with teacher-generated ChatML entries from es-legal-priv. 10 BOE articles, 1,148 train + 20 held-out eval items: - Each entry cites specific precepts (articuloscitados); those sections are extracted from the norm markdown and embedded as a CONTEXTO block in the user turn (up to 9,000 chars). - The system prompt enforces grounded behavior: answer…
Independent publisher
Jason Jiménez Cruz
jasonjimnz
Data, intelligence & open-source experimentation. Building in public, exploring models and knowledge systems, and making local AI accessible on a budget. Building, testing, and sharing from my lab.
Models in Library2
Datasets in Library0
Models on Hugging Face15
Followers2
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Question answering.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Third pre-alpha from Tyness Train, an agent-guided fine-tuning harness for small LLMs on low-VRAM GPUs. This model is RAG-style grounded (answers only from provided norm excerpts) and adds two confirmed recipe upgrades: a structured METADATOS block in the system prompt (official identifiers, dates, rank, department, article-title index) and adversarial correction pairs (user asserts a false premise → the model corrects it with the exact citation). Evaluated on fresh, uncontaminated teacher-generated sets: 200 questions per context style (never part of any training split), each grounded in a specific precept, judged by an LLM referee (glm5.3-flash): correct / partial / incorrect + 0–1 score.…