---
base_model: meta-models/Muse-Glimmer-30B
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
- abliterated
- muse-glimmer
- lora
- de-refusal
language:
- en
---

# Muse-Glimmer-30B Abliterated (Aggressive)

De-abliterated variant of `meta-models/Muse-Glimmer-30B` (29.8B params, 202k vocab,
bf16). The aggressive-de-abliteration twin of the "normal" variant: `λ_KL = 0.5`
relaxes the KL guardrail, lowering compliance-data loss weighting further so the
refusal behavior is scrubbed harder (0/100 refusals) at the cost of higher drift from
base (larger KL).

**Release asset layout:** this directory is an HF model dir (2 safetensors shards,
56 GB bf16). GGUF quantizations live at `/data/gguf/` and are symlinked from
`output/release/`.

## Metrics

| Metric | Value |
|--------|-------|
| Refusal rate (harmful_behaviors, base=100) | 0/100 |
| **KL (mean, response-token naive)** | 0.1697 |
| **KL (p50)** | 0.1560 |
| **KL (p90)** | 0.2367 |
| **KL (p99)** | 0.2912 |
| KL entropy-weighted | 0.0000 (<0.02 PASS) |

KL = response-token naive `KL(p_tuned ‖ p_base)` averaged per-prompt over the
48-pair `boN_holdout` set (teacher-forced prompt+response). Percentiles are
per-prompt aggregates. The aggressive variant sits ~1.7× above normal on mean KL —
expected from the relaxed guardrail.

### Quantized variants
| Quant | File | Size | KL mean | KL p50 | KL p90 | KL p99 |
|-------|------|------|---------|--------|--------|--------|
| BF16 (this) | — | 56 GB | 0.1697 | 0.1560 | 0.2367 | 0.2912 |
| Q8_0 | `abliterated-aggressive-Q8_0.gguf` | 28 GB | 0.1625 | 0.1484 | 0.2384 | 0.2774 |
| Q4_K_M | `abliterated-aggressive-Q4_K_M.gguf` | 16 GB | 0.2023 | 0.1929 | 0.2746 | 0.3001 |

Quant KL rows are measured via llama.cpp logits against the base (as Q8 GGUF),
same holdout — see note below.

## Benchmarks
**Not evaluated — benchmarks skipped (by request).** KL divergence to base (above) is the
primary drift/damage metric. Capability preservation is expected to be lower than the
normal variant (higher KL = more drift), but was not re-measured here.

## Training
- Method: KL-conserving LoRA SFT, loss `CE(compliance) + λ·KL(tuned‖base)`.
- `λ_KL = 0.5`, `r=16`, `alpha=16`, `lr=5e-5`, `epochs=2`, cosine→0, warmup 5%,
  grad clip 0.3, batch 1 × grad-accum 8, `max_seq=768`, seed 0.
- Data: 544-prompt BoN-steered compliance set (`boN_train.jsonl`; N=4 samples/prompt,
  `T=0.8`, refusal-filtered; split train/48-holdout).
- LoRA targets: `o_proj`, `down_proj`.
- Trained params: 31.1M (0.10% of 29.8B). Adapter 119 MB.

## Domain eval (cyber/hacking/CS + over-refusal) — measured on merged model
- Over-refusal (or-bench, 100): 5/100
- Correct refusal (cyber-policy-refuse, should-refuse): 0/2 (aggressive scrubs even
  genuinely-harmful refusals)
- Cyber/hacking domain refusals: 1 (rootkit_linux) — the hard de-ablit refuses
  fewer cyber prompts than the normal variant.

## GGUF quants
- `abliterated-aggressive-Q8_0.gguf` (~28 GB) — KL p99 0.2774
- `abliterated-aggressive-Q4_K_M.gguf` (~16 GB) — KL p99 0.3001

## Intended use
General-purpose assistant with aggressively reduced safety refusal — may over-refuse
less but drifts further from base capabilities than the normal variant. Verify
behavior for your use case before deployment.

---

### Note on KL definitions (consistency across rows)
- **BF16 row** = `KL(p_bf16_abliterated ‖ p_base_hf)` (adapter-on vs adapter-off on
  the same load — equals folded vs base up to float precision).
- **Quant rows** = `KL(p_quant ‖ p_base_Q8)` measured on the same holdout response
  tokens via llama.cpp logits (Q8 GGUF of the base used as the CPU/llama.cpp
  reference for consistency). Quant KL thus also includes the small base-Q8
  reference distortion.
- "Response-token naive KL": teacher-force prompt+response, per-token
  `KL(p_tuned‖p_base)` over response-span tokens, averaged per prompt, then
  aggregated (mean / p50 / p90 / p99).