jasonjimnz/tyness-boe-1.2b-pre-alpha

question-answering model by jasonjimnz

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

The first model trained end-to-end with Tyness Train, an agent-guided fine-tuning harness for small LLMs on low-VRAM GPUs. This is a pre-alpha release: it proves the full pipeline (dataset → QLoRA SFT on a GTX 1060 6GB → merge → GGUF → evaluation) and documents honest findings, including negative ones. Tyness Train is a harness for fine-tuning 1B–3B models on 6GB VRAM GPUs. This first release validates the whole pipeline on a deliberately hard, knowledge-dense domain: Source: consolidated Spanish legislation published by the Agencia Estatal Boletín Oficial del Estado (BOE), reused per its open-data conditions, via legalize-es (markdown per norm, YAML frontmatter). Entries: teacher-generated ChatML conversations (question / grounded answer), 1,148 training samples + 20 held-out eval items, filtered to 10 BOE articles: Methodology: Judged by an LLM referee (glm5.3-flash) on 20 held-out questions, verdict per item: correct / partial / incorrect, against the expected answer and the key reason.…

jasonjimnz/tyness-boe-1.2b-pre-alpha on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-08T08:32:15.498Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Evaluation & findings

Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

jasonjimnz/tyness-boe-1.2b-pre-alpha is a question-answering model repository published by jasonjimnz on Hugging Face. The source reports the peft library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: question-answering
Library: peft
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 1,170,340,608
Architecture: Lfm2ForCausalLM
License: other
Access: Not gated by Hugging Face
Created: 2026-10-08T06:28:37.000Z
Last modified: 2026-10-08T06:29:07.000Z

Compatibility and lineage

Reported languages: es

Reported base models: LiquidAI/LFM2.5-1.2B-Base

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion