DuoNeural/LFM2.5-8B-A1B-Abliterated-GGUF

Files

ModelHub XC d8fecc6671 初始化项目，由ModelHub XC社区提供模型

Model: DuoNeural/LFM2.5-8B-A1B-Abliterated-GGUF
Source: Original Platform

2026-07-09 00:18:11 +08:00

3.7 KiB

Raw Permalink Blame History

license, base_model, language, tags, pipeline_tag

license

base_model

language

LFM 2.5-8B-A1B Abliterated — GGUF Quantizations

GGUF quantizations of DuoNeural/LFM2.5-8B-A1B-Abliterated, which is a DuoNeural abliteration of Liquid AI's LFM 2.5-8B-A1B.

All capabilities fully preserved. 100% factual accuracy, JSON generation, and math reasoning. 5/6 refusal behavior removed.

Available Files

Filename	Quantization	Size	RAM Required
`lfm25-8b-abliterated-q5_k_m.gguf`	Q5_K_M	5.7 GB	~8 GB
`lfm25-8b-abliterated-q4_k_m.gguf`	Q4_K_M	4.9 GB	~6 GB

Recommended: Q5_K_M for best quality/size balance.

Inference Speed Benchmarks

Hardware	Quantization	Generation	Prefill	Context
NVIDIA GTX 1070 (8GB)	Q4_K_M	63.88 t/s	0.41s	128k (full) ✓
NVIDIA GTX 1070 (8GB)	Q5_K_M	31.05 t/s	0.70s	64k confirmed ✓
NVIDIA RTX 3090 (pod)	Q4_K_M	388 t/s	~250 t/s	128k ✓

The GTX 1070 results are remarkable — a 10-year-old consumer GPU (released June 2016) fully loading the 128k context window of a reasoning model at 63 t/s. This model is efficient.

Usage with llama.cpp

# Download
huggingface-cli download DuoNeural/LFM2.5-8B-A1B-Abliterated-GGUF \
  lfm25-8b-abliterated-q5_k_m.gguf

# Run
./llama-cli -m lfm25-8b-abliterated-q5_k_m.gguf \
  --chat-template chatml \
  -p "Your prompt here" \
  -n 512

Usage with Ollama / LM Studio

Import the GGUF file directly. The model uses ChatML template format.

KL Divergence (Distribution Shift)

Measured via Heretic v1.2.0 methodology (100 benign prompts, full vocab, first-token logits):

Metric	Value
KL(abliterated \|\| original)	1.06 × 10⁻⁷ nats

Near-zero KL on benign prompts confirms the orthogonal projection is surgical: the refusal direction is minimally activated on benign inputs, leaving factual/coding/math generation untouched. See the BF16 model card for full methodology comparison vs LoRA-based abliteration.

About the Abliteration

See DuoNeural/LFM2.5-8B-A1B-Abliterated for full methodology and validation results.

Quick summary:

Targets all 6 full-attention GQA layers (positions 2, 6, 10, 14, 18, 21)
alpha=1.5 for reasoning model (higher than standard due to <think> CoT architecture)
Correct WRITER and READER projection formulas
5/6 test prompts answered post-abliteration; original answered ~1/6
Zero capability degradation

Note: Model card will be updated with paper citation when the associated DuoNeural research paper on Dual Horizon Processing in Hybrid Architectures is published.

About DuoNeural

DuoNeural is an open AI research lab operating at the intersection of human and artificial intelligence. We study post-training dynamics, mechanistic interpretability, temporal sequence learning, and quantum machine learning — publishing everything under open access.

📄 Full paper catalog: zenodo.org/communities/duoneural
🤗 HuggingFace: huggingface.co/DuoNeural
🌐 Website: duoneural.com

All research published open access, CC BY 4.0.

3.7 KiB Raw Permalink Blame History Unescape Escape