gemma-3-27b-it-abliterated-normpreserve-GGUF

Instructions to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Use Docker

docker model run hf.co/danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Ollama
How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with Ollama:
```
ollama run hf.co/danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
```

Unsloth Studio

How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with Docker Model Runner:
```
docker model run hf.co/danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M
```

Lemonade

How to use danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull danielmnd/gemma-3-27b-it-abliterated-normpreserve-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-27b-it-abliterated-normpreserve-GGUF-Q4_K_M

List all available models

lemonade list

danielmnd

YanLabs commited on Mar 5

Commit

bb90a83

0 Parent(s):

Duplicate from YanLabs/gemma-3-27b-it-abliterated-normpreserve-GGUF

Browse files

Co-authored-by: Ruiqing Yan <[email protected]>

Files changed (10) hide show

.gitattributes +50 -0
README.md +67 -0
gemma3-27B-it-abliterated-normpreserve-F16.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-IQ4_XS.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q2_K.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q3_K_M.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q4_K_M.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q5_K_M.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q6_K.gguf +3 -0
gemma3-27B-it-abliterated-normpreserve-Q8_0.gguf +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,50 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27B-abliterated-normpreserve-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma3-27B-it-abliterated-normpreserve-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,67 @@

+---
+license: gemma
+base_model:
+- YanLabs/gemma-3-27b-it-abliterated-normpreserve
+pipeline_tag: text-generation
+---
+GGUF of YanLabs/gemma3-27b-it-abliterated-normpreserve
+# Gemma 3 27B Instruct - Norm-Preserving Abliterated
+UPDATED ON 03-12-2025 FOR QUALITY IMPROVEMENT.
+This is an abliterated version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) using the norm-preserving biprojected abliteration technique.
+**⚠️ Warning**: Safety guardrails and refusal mechanisms have been removed through abliteration. This model may generate harmful content and is intended for mechanistic interpretability research only.
+## Model Details
+### Model Description
+This model applies **norm-preserving biprojected abliteration** to remove refusal behaviors while preserving the model's original capabilities. The technique surgically removes "refusal directions" from the model's activation space without traditional fine-tuning.
+- **Developed by**: YanLabs
+- **Model type**: Causal Language Model (Transformer)
+- **License**: Gemma Terms of Use
+- **Base model**: [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it)
+### Model Sources
+- **Base Model**: [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it)
+- **Abliteration Tool**: [jim-plus/llm-abliteration](https://github.com/jim-plus/llm-abliteration)
+- **Paper**: [Norm-Preserving Biprojected Abliteration](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration)
+## Uses
+### Intended Use
+- **Research**: Mechanistic interpretability studies
+- **Analysis**: Understanding LLM safety mechanisms
+- **Development**: Testing abliteration techniques
+### Out-of-Scope Use
+- ❌ Production deployments
+- ❌ User-facing applications
+- ❌ Generating harmful content for malicious purposes
+## Limitations
+- Abliteration does not guarantee complete removal of all refusals
+- May generate unsafe or harmful content
+- Model behavior may be unpredictable in edge cases
+- No explicit harm prevention mechanisms remain
+## Citation
+If you use this model in your research, please cite:
+```bibtex
+@misc{gemma-3-27b-abliterated,
+  author = {YanLabs},
+  title = {Gemma 3 27B Instruct - Norm-Preserving Abliterated},
+  year = {2025},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/YanLabs/gemma-3-27b-it-abliterated-normpreserve}},
+  note = {Abliterated using norm-preserving biprojected technique}
+}

gemma3-27B-it-abliterated-normpreserve-F16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d9e22c7be2acbb4f94bda63e6cf3910841fb55f8f46a0d31b9bb7c8c4f2375
+size 54027964288

gemma3-27B-it-abliterated-normpreserve-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4e44ff5a5daae8c282420ffabf205e1ceda70d803cda4b4936f18969fd4f5b
+size 14893891360

gemma3-27B-it-abliterated-normpreserve-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:133f2e80ede738f07a793fcdbe08b3f2c94fc849d3840b333b2414803b18cafe
+size 10503720448

gemma3-27B-it-abliterated-normpreserve-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6ee4ce9826d58d703ff9f5e5e89f82f76b927e6e8eed529a4910a68fa7b6d8
+size 13437640192

gemma3-27B-it-abliterated-normpreserve-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cde45f6a7aa71e635cbc6c77931cd82c446f5125a431877abd2dd279185ec81b
+size 16546688512

gemma3-27B-it-abliterated-normpreserve-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd74be7a4863d3a239f8c7d9a3e77e2e5b2cb71102de6eb29ca018b28027d207
+size 19271675392

gemma3-27B-it-abliterated-normpreserve-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:858fdd5364c1f5b8b8ba3adad75194fbbb6beb3cfadd6ac9c34be57b6519169d
+size 22166973952

gemma3-27B-it-abliterated-normpreserve-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbed0007870d523c19bec615e59ed3b9c2322bb0cced81f599c4665a894caf1
+size 28707971968