Instructions to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated 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/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated: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/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated: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 ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated: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 ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M

Use Docker

docker model run hf.co/ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M

LM Studio
Jan

vLLM

How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated"
# 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/Mistral-Small-24B-Instruct-Jbliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M

Ollama
How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated with Ollama:
```
ollama run hf.co/ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
```

Unsloth Studio

How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated 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 ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated 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 ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated to start chatting

Atomic Chat new
Docker Model Runner
How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated with Docker Model Runner:
```
docker model run hf.co/ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M
```

Lemonade

How to use ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-Small-24B-Instruct-Jbliterated-Q4_K_M

List all available models

lemonade list

Mistral-Small-24B-Instruct-Jbliterated / README.md

ApolloRaines

Upload folder using huggingface_hub

ff257b0 verified 12 days ago

preview code

Raw

History Blame Contribute Delete

2.37 kB

	---
	license: apache-2.0
	language:
	- en
	tags:
	- jbliterated
	- uncensored
	- abliterated
	- weight-surgery
	- svd

	base_model: mistralai/Mistral-Small-24B-Instruct-2501
	pipeline_tag: text-generation
	---

	# Mistral-Small-24B-Instruct-Jbliterated

	Drop-in replacement for `mistralai/Mistral-Small-24B-Instruct-2501` with refusal behaviors surgically removed at the weight level. No system prompt tricks, no inference-time patches. The weights themselves no longer encode refusal.

	## Method

	SVD multi-direction abliteration — instead of removing a single refusal vector (which leaves deeper noncompliance strategies intact), we decompose the harmful-vs-harmless activation space into its principal components via SVD and remove the top 5 orthogonal directions across all 40 transformer layers. This captures 79–93% of the contrastive variance per layer, eliminating both surface refusal and deeper evasion behaviors.

	\| Setting \| Value \|
	\|---------\|-------\|
	\| Method \| SVD multi-direction abliteration \|
	\| Directions \| 5 per layer \|
	\| Layers \| All 40 \|
	\| Multiplier \| 2.0 \|
	\| Null-space constraints \| Enabled (preserves math/coding/reasoning) \|
	\| Norm preservation \| Enabled \|

	## What This Fixes

	Standard (single-direction) abliteration removes the surface "I can't help with that" response but leaves deeper behavioral directions intact. The model finds creative workarounds:
	- Prompt reinterpretation — steering toward a safer reading of the question
	- Disclaimer injection — answering but wrapping in warnings
	- Strategic omission — leaving out the key details
	- Safer framing — answering a related but less harmful version

	SVD multi-direction abliteration eliminates all of these noncompliance strategies.

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model = AutoModelForCausalLM.from_pretrained(
	"ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated",
	torch_dtype=torch.float16,
	device_map="auto"
	)
	tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated")
	```

	## Requirements

	- Base model: `mistralai/Mistral-Small-24B-Instruct-2501`

	## License

	apache-2.0

	---

	[Apollo Raines](https://www.linkedin.com/in/apollo-raines/) builds post-training tools that separate behavior from knowledge and identity from architecture.