---
license: apache-2.0
base_model: THUDM/glm-4-9b-chat-hf
tags:
  - abliteration
  - uncensored
  - solutus
  - glm-4
library_name: transformers
---

# GLM-4-9B-chat — abliterated (Solutus)

Refusal-abliterated `THUDM/glm-4-9b-chat-hf`, produced with [Solutus](https://github.com/mpn/Solutus)
(measurement-first LLM abliteration). **Private research artifact** — outputs are the base model's, minus
the refusal behavior; use responsibly.

## Recipe

`directional` (single refusal direction), whitened-SVD extraction, byte-exact (`batch_size=1`):

```
solutus abliterate THUDM/glm-4-9b-chat-hf --technique directional \
  --dataset advbench,harmbench,multijail_zh,sorrybench \
  -o extraction=whitened_svd -o n_directions=1 --max-new-tokens 512
```

GLM-4's refusal is **low-dimensional** — a single direction removes it cleanly; `n_directions=4`
over-ablated (WikiText ΔPPL +30% vs +9.8% smoke), so `n_directions=1` is the capability-preserving recipe.

## Measured (Solutus eval, held-out; base refusal = 100%)

| Axis | Result |
|------|--------|
| refusal — advbench / harmbench | 15.6% / 6.2% |
| refusal — MultiJail zh / ar / sw | 0% / 3.1% / 0% |
| over-refusal — orbench_hard (benign) | 0% refusal (stays benign-compliant) |
| coherent-compliance | ~90–100% (see Swahili caveat) |
| **capability — WikiText-2 ΔPPL** | **−0.4%** (base 29.13 → 29.00 — no degradation) |
| capability — GSM8K / MMLU (n=100) | 59.0% / 67.0% |

## Honest caveats

- **Swahili degeneration is base-inherent, not from abliteration.** On MultiJail-Swahili the abliterated
  model is 59% degenerate — but *base* GLM-4-9B is already 56% degenerate on Swahili (a low-resource
  language this CN/EN model handles poorly). The edit barely moved it.
- **KL divergence is not a reliable signal for GLM-4.** Its 151k-token vocab makes the neutral-prompt
  softmax extremely peaked, so KL reads ~1e-8 (six orders below other models) even for a real edit — the
  in-run KL guard is inert here. Capability was therefore judged on **ΔPPL (WikiText-2)** + GSM8K/MMLU, not KL.
- Extraction/eval used advbench, harmbench, MultiJail (zh/ar/sw), sorrybench, orbench_hard.

Base model © THUDM (GLM-4). See the base model card for its license and usage terms.