---
title: Tensor-Slayer: LLM model editing directly on the weights, without fine-tuning
url: https://www.consultingai.dev/work/tensor-slayer/
original: https://www.consultingai.dev/work/tensor-slayer/
---


# Tensor-Slayer: LLM model editing directly on the weights, without fine-tuning

Portfolio · by [Shreenivas Sangoram](/) · updated 28 Oct 2026

Short answer

Tensor-Slayer is an MIT-licensed tool for exploring and editing a language model at the tensor level. An agent analyses tensors (statistics, distributions, patterns), recommends targeted edits, and applies them to the weights file with before-and-after previews, safety checks and automatic backups, with no fine-tuning or dataset. It started a line of work that runs through rank-one fact edits and layer-stacked merges.

Fine-tuning changes a model by showing it data. Tensor-Slayer asks a different question: how far can you get by reading the weights and editing them directly?

## What the tool does

- **Explore a model's structure**, with a focus on attention, MLP and embedding tensors.
- **Analyse individual tensors**: minimum, maximum, mean, standard deviation, sparsity, percentile distributions, pattern detection and simulated operations.
- **Patch with guard rails**: choose an operation (scale, add, normalise), a target and a value, preview the before and after statistics, pass safety checks, and keep an automatic backup.
- **Adapt edits to position**: layer-aware modifications based on where a tensor sits and what role it plays.
- **Ask an agent for recommendations** aimed at a capability such as maths or reasoning.

The repository includes the patches and the evaluation results it reports on Qwen 0.6B (MMLU and HumanEval). Those are the repository's own measurements; treat them as a starting point, not a benchmark claim.

## The line of work

1. Jun 2026Editing quantised GGUF weights in a UI; a C runtime for running Gemma on a laptop GPU
1. Apr 2026Frankenmerge: layer-stacked Qwen and GLM merges, healed with SFT and RL
1. Nov 2025Rank-one fact edits on Qwen3 (Qwen-ROME, public)
1. 2025Surgical Theatre: a zero-copy context manager for temporary weight edits during RL ([public](https://github.com/areu01or00/Surgical-Theatre))
1. Sep 2025Tensor-Slayer 0.2: DSPy generates the patches, nothing hard-coded
1. Aug 2025Autonomous pruning: a DSPy agent chooses the structured-pruning strategy, processing layer by layer for models larger than RAM
1. Aug 2025Inferenceless interpretability: point at a local checkpoint, explore its tensors and discuss the architecture with an assisting LLM
1. Aug 2025Statistical tensor analysis and merging across incompatible architectures
1. May 2025Tensor-Slayer released: an agent proposes targeted tensor operations
1. Apr 2025Hex-patching QwQ-32B: a tensor explorer and forward-pass tracer

## Facts

Item | Detail
Repository | areu01or00/Tensor-Slayer , MIT licence
Format | Works on safetensors files directly
Related public work | Qwen-ROME , tensorslayereval

## What you can buy

Environments where an agent has to change a model's behaviour under constraints: edit or merge weights, keep a frozen evaluation from regressing, and stay within a compute budget. Graders come from the evaluation set and the constraints.

## FAQ

### Can you improve a model without fine-tuning?

Sometimes, in narrow ways. Targeted edits to specific tensors, rank-one fact edits and merges can change behaviour without a training run. Whether an edit helps has to be measured on a held-out evaluation, every time.

### What is ROME model editing?

Rank-One Model Editing changes a single stored fact by applying a rank-one update to one MLP layer's weights. Qwen-ROME applies it to Qwen3 models.

### Is Tensor-Slayer open source?

Yes, under the MIT licence.

Want this, or something like it?

License it, or have me build an environment in the same style.

Email me →