feat(indexing): sync CITATION.cff, codemeta.json & DOIs (10.5281/zenodo.21209973, hal-05847496v1)
529c139 verified | library_name: peft | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | |
| tags: | |
| - unsloth | |
| - lora | |
| - einsof | |
| - polydim | |
| - stiefel-manifold | |
| - formal-theorems | |
| - pmtp | |
| license: apache-2.0 | |
| # DeepSeek-R1-Distill-Qwen-14B-Einsof-LoRA (v020) | |
| **Autor:** Ariel García Traba (Independent Research / EinsofOS) | |
| **Institución:** Einsof Research / Antigravity Autonomous Compute | |
| **Entrenado en:** Google Colab Plus (NVIDIA A100-SXM4-40GB) | |
| **Modelo Base:** `deepseek-ai/DeepSeek-R1-Distill-Qwen-14B` | |
| **Corpus Canónico:** 1.736 teoremas formales de PostgreSQL 16 (`polydim_vec_db`) + 13 Leyes de Silicio de Einsof. | |
| ## Hiperparámetros de Entrenamiento | |
| - **LoRA Rank (r):** 16 | |
| - **LoRA Alpha (α):** 16 | |
| - **Target Modules:** `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` | |
| - **Parámetros Entrenables:** 68,812,800 | |
| - **Precisión Nativa:** BF16 nativo (A100 SXM4) | |
| - **Optimizador:** `adamw_8bit` | |
| - **Pérdida Final de Entrenamiento:** 0.7225 | |
| ## Uso con Unsloth / Hugging Face Transformers | |
| ```python | |
| from unsloth import FastLanguageModel | |
| import torch | |
| model, tokenizer = FastLanguageModel.from_pretrained( | |
| model_name="polydim-einsof/DeepSeek-R1-Distill-Qwen-14B-Einsof-LoRA", | |
| max_seq_length=4096, | |
| dtype=torch.bfloat16, | |
| load_in_4bit=True, | |
| ) | |
| FastLanguageModel.for_inference(model) | |
| ``` | |
| --- | |
| ## Global Scientific Indexing & Persistent Identifiers (CERN Zenodo / CNRS HAL / JST Jxiv / OSF / ORCID) | |
| - **Author:** Ariel H. García Traba ([ORCID: 0009-0001-2787-6067](https://orcid.org/0009-0001-2787-6067)) | |
| - **Affiliation:** EinsofOS Independent Research / POLYDIM Research Initiative | |
| - **CERN / Zenodo Primary DOI:** [10.5281/zenodo.21136742](https://doi.org/10.5281/zenodo.21136742) | |
| - **CERN / Zenodo Secondary DOI:** [10.5281/zenodo.21209973](https://doi.org/10.5281/zenodo.21209973) | |
| - **CNRS / HAL Open Science (France):** [`hal-05847496v1`](https://hal.science/hal-05847496v1) | |
| - **Center for Open Science (OSF):** [`https://osf.io/za3s7`](https://osf.io/za3s7) | |
| - **JST / Jxiv Preprint Server (Japan):** `Jxiv ID 7040` | |
| - **Canonical Papers & LaTeX Archive:** [`Polydim-Einsof/POLYDIM-EINSOF-Canonical-Papers-V1550`](https://huggingface.co/datasets/Polydim-Einsof/POLYDIM-EINSOF-Canonical-Papers-V1550) | |
| ```bibtex | |
| @article{garciatraba2026polydim, | |
| title = {Dimension Is All You Need: Eradicating the 1D Worm Collapse via Native High-Dimensional Manifold Inter-Process Communication in S^{D-1}}, | |
| author = {Garc{\'i}a Traba, Ariel H.}, | |
| year = {2026}, | |
| month = {nov}, | |
| publisher = {Zenodo / CERN & HAL Open Science}, | |
| doi = {10.5281/zenodo.21209973}, | |
| url = {https://doi.org/10.5281/zenodo.21209973}, | |
| note = {Primary DOI: 10.5281/zenodo.21136742; HAL ID: hal-05847496v1; OSF: https://osf.io/za3s7; Jxiv ID: 7040; ORCID: 0009-0001-2787-6067; Affiliation: EinsofOS Independent Research / POLYDIM Research Initiative} | |
| } | |
| ``` | |