Downloads · 30 days
3.2K
50% of all-time downloads
olekk/gemma-4-E4B-it-abliterated-litert-lm
gemma-4-E4B-it-abliterated-litert-lm is a text generation model from olekk. Use it when you need the model to write or continue text. It is set up for litert-lm. The card lists the license as apache-2.0.
An abliterated (refusal-removed) build of Gemma 4 E4B, packaged as a single .litertlm for the LiteRT-LM runtime: mobile wNa8o8 quantization (mixed int4/int8 weights + static int8 activations), Multi-Token Prediction (…
Downloads · 30 days
3.2K
50% of all-time downloads
All-time downloads
6.3K
Public
Repo size
3.7 GB
Likes
12
Public
Click a slice to open those files.
.litertlm3.7 GB · 100%
From the Hugging Face model README
.litertlm)An abliterated (refusal-removed) build of Gemma 4 E4B, packaged as a
single .litertlm for the LiteRT-LM runtime: mobile wNa8o8
quantization (mixed int4/int8 weights + static int8 activations), Multi-Token
Prediction (MTP) speculative decoding, and the multimodal encoders - all
intact. Runs on Android / desktop / iOS via CPU (XNNPACK) or GPU (ML Drift).
Safety. Refusals are removed. This model will comply with harmful requests. Research / personal use only - you own the outputs.
Rather than rebuilding a .litertlm from scratch (public tooling can't reproduce
Gemma 4's MTP wiring), the working litert-community/gemma-4-E4B-it-litert-lm
artifact was patched in place: only the o_proj/down_proj weights inside
the quantized prefill_decode.tflite were edited, so the embedder, tokenizer and
MTP drafter survive byte-for-byte.
Because a norm-preserving biprojected abliteration edit is smaller than the int4 quantization step, plain round-to-nearest requant erases it. A directional error-feedback requantizer preserves the refusal-direction removal on the int4 grid. Full method + code: repo.
o_proj/down_proj int4 codes
changed.This is unbenchmarked territory (QAT + abliteration + int4 requant); no perplexity / standardized refusal-rate benchmark has been run. Treat quality claims as directional.
uv tool install litert-lm
litert-lm run gemma-4-E4B-it-abliterated.litertlm \
--backend=gpu --enable-speculative-decoding=true \
--prompt="…"
Or use the minimal Android app in the repo.
.litertlm but not identical.Base: Google Gemma 4 E4B + LiteRT-LM + litert-community .litertlm
(all Apache-2.0). Method: biprojection (grimjim) / p-e-w/heretic; Gemma-4
recipe from TrevorS/gemma-4-abliteration. The int4 in-place patch is original.
Base Gemma 4 Prohibited Use Policy
applies. Licensed Apache-2.0; modifications = abliteration + int4 requant.