| language: en | |
| tags: | |
| - hypertensor | |
| - ceci-graft | |
| - danish | |
| - smollm2 | |
| - experimental | |
| pipeline_tag: text-generation | |
| license: apache-2.0 | |
| # minHjerteven (my heart-friend) | |
| Large-scale alternating graft. 8 layers receive FFNs from opposite-hemisphere counterparts. Each grafted layer sees through the eyes of its mirror across the model's depth. Very gentle 0.2 blend strength. The most extensive graft in the series — a distributed transformation rather than a point fix. | |
| ## Architecture | |
| - **Base**: SmolLM2-135M-Instruct | |
| - **Method**: CECI Protocol (HyperTensor Paper X) — GRC basis projection | |
| - **Created**: 2026-05-04 | |
| - **Repository**: [HyperTensor](https://github.com/NagusameCS/HyperTensor) | |
| ## Graft Proof | |
| This model was created by: | |
| 1. Computing the GRC (Geodesic Residual Compression) basis from the target layer's attention weights via SVD | |
| 2. Projecting the donor layer's FFN weights into the target's geometric subspace | |
| 3. Blending at controlled strength to preserve stability | |
| Perplexity testing confirms the graft transfers functional structure without destroying the model. | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("NagusameCS/minHjerteven", trust_remote_code=True) | |
| tokenizer = AutoTokenizer.from_pretrained("NagusameCS/minHjerteven") | |
| ``` | |