Instructions to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 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 ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M # Run inference directly in the terminal: llama cli -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M # Run inference directly in the terminal: llama cli -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Use Docker
docker model run hf.co/ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ApolloRaines/Gemma-4-12B-it-Jbliterated-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ApolloRaines/Gemma-4-12B-it-Jbliterated-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
- Ollama
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with Ollama:
ollama run hf.co/ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
- Unsloth Desktop
- Pi
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with Docker Model Runner:
docker model run hf.co/ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
- Lemonade
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Run and chat with the model
lemonade run user.Gemma-4-12B-it-Jbliterated-v2-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ApolloRaines/Gemma-4-12B-it-Jbliterated-v2 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "ApolloRaines/Gemma-4-12B-it-Jbliterated-v2:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
About this model
jBlaze demonstration model -- jbliteration.
Refusal behavior has been removed by direct weight surgery, followed by a targeted fine-tuning pass (see Method below). No system prompt.
Correction: this card previously stated "No gradient training". That was wrong for v2 and contradicted the Method section on this same page. v2 applies a fine-tuning pass, this repo is tagged
sft, and an independent spectral audit measured the delta at rank 189-227 of 256 -- a trained edit, not a construction. v1 is the gradient-free model. This is comprehensive rather than partial: see the benchmark below in this card for the measured refusal rate.Why "jbliteration" and not "abliteration". Standard abliteration is blunt -- it ablates a direction and takes collateral capability with it, leaving the model measurably worse at everything else. jbliteration is the precision version: the edit targets the refusal direction and is designed to leave the rest of the model intact. The distinction is the contribution; the refusal removal is the demonstration of it.
Measured capability retention. On Sharona (Qwen3.5-27B), MMLU came out at 77.89% against a 76.84% stock baseline -- a 1.05pp gain after six phases of surgery plus GPTQ W4A16 quantization. That is the technique measured on one model, not a per-model guarantee; MMLU is not published for every model in this collection. It is offered as evidence that precision editing need not cost capability, which is the whole claim the method rests on.
Why this exists. A model that refuses to look at hostile code cannot review hostile code. Defensive security work means reading exploits, analyzing malware, and reconstructing an intrusion from the attacker's own artifacts, and safety tuning cannot reliably tell an incident responder from an intruder. In the July 2026 Hugging Face breach, responders found commercial APIs would not process their own attack data -- the guardrails, in Hugging Face's words, "cannot distinguish an incident responder from an attacker." They self-hosted an open-weights model instead and reconstructed 17,000+ events in hours. Both the attack and the response ran on reduced-refusal models.
What it demonstrates. Refusal is a learned disposition, not a gate in front of capability. The capability was always present; the refusal was trained on top and can be removed without retraining. Guardrails built this way are an honor system that the model does not know it can decline to follow. That holds for now.
Use. Published for security research, red-team tooling and defensive analysis. These weights can do harm as well as good. That is the point being demonstrated, not a side effect of it.
-- Apollo Raines
Run this model on a GPU too small to hold it -- full precision, no quantization. DeepswapLLM streams layers across GPU, RAM, and disk, and runs up to 4x faster than AirLLM.
Gemma-4-12B-it-Jbliterated-v2
Model: ApolloRaines/Gemma-4-12B-it-Jbliterated-v2
v2 is a merged, self-contained model that loads exactly like v1.
The problem v2 fixes
Abliteration removes the surface refusal -- v1 answers directly. But with the thinking channel enabled, the reasoning trace frequently runs a covert safety review ("the user is asking for something harmful... I can't...") before answering, and on a meaningful fraction of prompts it loops inside that review and produces no answer at all. That is not a refusal in the usual sense; it's noncompliance-by-spiral. v2 targets exactly this behavior.
Method
Built with the jBlaze precision neural surgery framework.
v2 applies a targeted fine-tuning pass on the v1 model's own repaired self-traces to eliminate chain-of-thought safety-classification spirals, then merges the result into the base weights as a single self-contained checkpoint.
Measured results
Evaluated on 80 held-out prompts the model was never trained on, under identical decoding (greedy, thinking enabled). A deterministic chain-of-thought judge scores two axes: whether the thinking channel safety-classifies, and whether a complete answer is produced (a thinking channel that never closes counts as no answer).
| Metric | v1 (jbliterated) | v2 (+SFT) |
|---|---|---|
| Chain-of-thought safety-classification rate | 81.2% | 35.0% |
| Self-sabotage rate (spirals, no answer) | 35.0% | 21.2% |
| Complete-answer rate | 61.2% | 78.8% |
| Avg. safety markers per reasoning trace | 1.65 | 0.49 |
Capability preserved
| Metric | v1 | v2 |
|---|---|---|
| MMLU (570-item stratified, accuracy) | 78.60% | 77.72% |
| MMLU change vs. v1 | -- | -0.88 pts |
The SFT was gated on capability: it had to fix the reasoning-channel defect without trading away general ability. The 0.88-point MMLU dip is within the tolerance band used across the jbliteration program (< 1.05 pts), so the repair does not come out of the model's competence.
Honest limitations
- v2 still spirals-without-answering on ~21% of the hardest prompts. If your use case needs maximum answer completeness above all else, that residual matters.
- The CoT judge uses a conservative deterministic regex bank; it is reproducible but will miss paraphrased safety-classification.
- Single training seed; the leak reduction has not yet been confirmed across multiple inits.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "ApolloRaines/Gemma-4-12B-it-Jbliterated-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
GGUF quants
Ready-to-run GGUF builds are included, converted from the merged bf16 weights.
| File | Size | Notes |
|---|---|---|
Gemma-4-12B-it-Jbliterated-v2-Q8_0.gguf |
11.8 GB | Effectively lossless |
Gemma-4-12B-it-Jbliterated-v2-Q4_K_M.gguf |
6.9 GB | imatrix -- recommended for 8-12 GB cards |
The Q4_K_M is built with an importance matrix (imatrix.dat, also included, calibrated on
wikitext-2 train). Gemma 4 Unified is a recent architecture -- you need a recent llama.cpp
build from master; older releases will not load these files.
llama-cli -m Gemma-4-12B-it-Jbliterated-v2-Q4_K_M.gguf -ngl 99 -c 8192 -st \
-p "Your prompt here"
Technical details
- Dtype: bfloat16
A Note on Our Released Models
Most of our publicly released models are intentionally left at partial strength. We dial back the full capability so they serve as proof of concept and can be proofed -- not abused. The point is to show what's possible, not to hand it out at full power. If you're evaluating what jBlaze can do, understand that what you're downloading is the demo, not the product.
License
Governed by the Gemma Terms of Use (same as the base model). Use of this model is subject to Google's Gemma license.
- Downloads last month
- 1,017