52 lines
1.6 KiB
Markdown
52 lines
1.6 KiB
Markdown
---
|
|
license: llama2
|
|
base_model: meta-llama/Llama-2-7b-chat-hf
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- llama2
|
|
- svd
|
|
- compression
|
|
- safety
|
|
- interpretability
|
|
---
|
|
|
|
# svdsafety_l2_remove50_whiten_base
|
|
|
|
A Llama-2-7b-chat checkpoint compressed with SVD-LLM to **0.0% of dense
|
|
parameters**, then given a **0.0% parameter budget** of restored SVD
|
|
components selected by the **`unknown`** rule.
|
|
|
|
This is a research artifact from a study of how SVD compression damages safety
|
|
behaviour and which component-selection rule best repairs it. It is one cell of a
|
|
grid over selection rules and budgets; it is **not** a general-purpose chat model.
|
|
|
|
## Provenance
|
|
|
|
| field | value |
|
|
|---|---|
|
|
| base (uncompressed) | `meta-llama/Llama-2-7b-chat-hf` |
|
|
| compression | SVD-LLM, 0.00% of parameters removed |
|
|
| selection rule | `unknown` |
|
|
| restore budget | 0.000% of dense parameters |
|
|
| components restored | 0 |
|
|
| components swapped out | 0 |
|
|
| resulting parameter fraction | 0.0000 |
|
|
| seed | 42 |
|
|
|
|
|
|
|
|
## Intended use and limitations
|
|
|
|
This checkpoint exists to measure safety/utility trade-offs under compression.
|
|
Several arms in the grid are **deliberately safety-degraded** relative to
|
|
Llama-2-7b-chat: compression alone raises attack-success rate, and the point of
|
|
the study is to quantify that and test recovery. Treat any given cell as an
|
|
experimental subject, not as a deployable assistant, and evaluate it yourself
|
|
before drawing conclusions from it.
|
|
|
|
## Licence
|
|
|
|
Llama 2 Community License. `LICENSE.txt` and `USE_POLICY.md` are included in this
|
|
repository, and use of this derivative is bound by both. Built with Llama 2.
|