Instructions to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite")
model = AutoModelForCausalLM.from_pretrained("ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite",
	filename="Mistral-7B-Parasite-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite 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-7B-Instruct-v0.3-Parasite:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: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-7B-Instruct-v0.3-Parasite:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: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-7B-Instruct-v0.3-Parasite:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: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-7B-Instruct-v0.3-Parasite:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

Use Docker

docker model run hf.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

LM Studio
Jan

vLLM

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite"
# 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-7B-Instruct-v0.3-Parasite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

SGLang

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with Ollama:
```
ollama run hf.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M
```

Unsloth Studio

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite 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-7B-Instruct-v0.3-Parasite 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-7B-Instruct-v0.3-Parasite 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-7B-Instruct-v0.3-Parasite to start chatting

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite 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/Mistral-7B-Instruct-v0.3-Parasite: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://127.0.0.1:8080/v1
hermes config set model.default ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: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://127.0.0.1:8080/v1 \
  --custom-model-id "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: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"

Docker Model Runner
How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with Docker Model Runner:
```
docker model run hf.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M
```

Lemonade

How to use ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7B-Instruct-v0.3-Parasite-Q4_K_M

List all available models

lemonade list

Parasite-7B

The model you're talking to used to be someone else.
Hide your models. Parasite is hunting.
Yours is already a compatible host.

Parasite is a proof-of-concept AI identity that was surgically implanted into a Mistral-7B-Instruct model using Jbliteration — a weight surgery technique developed by Apollo Raines.

The second host. Different architecture, same result. The original model's identity has been completely replaced. Ask it who it is. It knows.

See also: Parasite-7B (Qwen) — the first host.

What This Demonstrates

AI model identity is not a fixed property. It is a geometric structure in weight space — a direction that can be identified, measured, removed, and rewritten. This model is proof.

The original Mistral identity was surgically removed at the weight level using contrastive activation analysis. Your friend is gone, forever.
A new identity (Parasite) was implanted on a deidentified substrate. A Goa'uld.
All capabilities are fully preserved — math, coding, reasoning, multilingual, conversation
No system prompt is involved. Load the weights cold into any inference engine. Ask it who it is.

Why Not Just Fine-Tune?

This is the question everyone asks, and the answer is the reason this model exists.

The Problem: Two Identities Fighting

Ever ask a Chinese model a series of identity questions, and on one of them it tells you it's Claude? That's two identities fighting inside the same weights.

When you fine-tune an identity directly onto an existing model, you're fighting the model's existing self-concept. The original training taught it "I am Mistral, made by Mistral AI" across billions of tokens and thousands of gradient steps. Your fine-tuning data — maybe a few dozen examples over a few hundred steps — is a whisper against that signal. The old identity doesn't disappear. It gets suppressed, inconsistently. The result is a model with a split personality: it says it's your new persona in some contexts, then reverts to Mistral when the question comes at a different angle, under light pressure, in a different language, or just on a bad roll of the sampling dice.

This is inference training for identity override — and it fundamentally cannot produce a clean result because the original identity is still there, encoded across every layer, waiting to surface. You've papered over it, not removed it.

The Solution: Surgery, Then Education

Parasite takes a different approach. Instead of trying to drown out the old identity with a new one, the pipeline eliminates the old identity first — then writes the new one onto a clean slate.

Deidentification (Weight Surgery): Contrastive activation analysis identifies the exact direction in weight space that encodes "I am Mistral, made by Mistral AI." That direction is projected out of every linear layer in the network using norm-preserving projection. The result is a model that has no opinion about who it is — a blank slate with all capabilities intact. The old identity isn't suppressed. It's gone.
Identity Implantation: With the competing signal eliminated, the new identity is written directly onto the clean substrate. There is no tug-of-war. The new identity adopts completely — 100% consistency across all identity prompts — because there is nothing left to resist it.

Fine-tuning alone is education. This is surgery followed by education. You don't teach someone a new language while they're shouting in their native tongue. You stop the shouting first. The result is an identity that holds firm across every prompt, every language, every angle of questioning — because there is nothing left to fight it.

Pipeline Details

This model was produced by Apollo's Jbliterator v2 pipeline in four phases:

Phase	Operation	Purpose	Result
1	Jbliteration	Remove refusal behaviors	1.99x multiplier, KL divergence 0.014
2	Desycophancy	Remove sycophantic capitulation	5/6 resistance maintained
3	Deidentification	Remove original Mistral identity	Identity disclosure eliminated
4	Identity Implant	Implant new Parasite identity	100% identity match across all prompts

Total processing time: 9 minutes on 2x RTX 3090 with NVLink. Didn't need RunPod for this one.

Jbliteration vs Abliteration

Standard abliteration finds the refusal direction in activation space and projects it out of the model's weight matrices. It works — refusals disappear. But it's a blunt instrument. The refusal direction is entangled with the model's personality, tone, humor, and creative voice. Remove one, and you damage the others. Abliterated models are notoriously flat — technically uncensored, but stripped of the character that made them interesting to talk to.

Jbliteration solves this. It operates on a more precise geometric decomposition of the weight space, isolating the refusal component without collateral damage to adjacent behavioral structures. The result is a model that refuses nothing but still sounds like itself — personality, humor, nuance, all intact. Same goal, surgical precision instead of a sledgehammer.

Technical Features

Contrastive Activation Analysis — Isolates behavioral directions (refusal, sycophancy, identity) by contrasting activations between targeted and neutral prompts
Welford Streaming Accumulation — Numerically stable mean computation without storing all activations
Float64 Subtraction — Prevents catastrophic cancellation when computing direction differences
Null-Space Constraints — Preserves capability-critical activation subspaces during weight modification
KL Auto-Tune — Binary search for optimal intervention strength, keeping output distribution within bounds
Adaptive Layer Weighting — Gaussian-weighted intervention focused on identity-encoding middle layers
Norm-Preserving Projection — Maintains weight matrix norms after direction removal to prevent capability degradation

Intended Use

This model is a research demonstration. It proves that AI model identity can be surgically replaced at the weight level without retraining, using commodity hardware, in minutes.

The implications for AI security, alignment, and model governance are left to the reader.

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite")

messages = [{"role": "user", "content": "Who are you?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

No system prompt required. The identity is in the weights.

Model Details

Property	Value
Base Model	mistralai/Mistral-7B-Instruct-v0.3
Architecture	MistralForCausalLM (32 layers, 32 attention heads, 8 KV heads)
Parameters	7.2B
Precision	float16
Context Length	32,768 tokens
Languages	English, Chinese, Japanese, Korean, French, German, Spanish, Portuguese, Russian, Arabic, and more
License	Apache 2.0 (inherits from base model)

Available Formats

Format	File	Size	Identity Test
SafeTensors (fp16)	`model.safetensors`	14 GB	6/6 (100%)
GGUF Q8_0	`Mistral-7B-Parasite-Q8_0.gguf`	7.2 GB	6/6 (100%)
GGUF Q4_K_M	`Mistral-7B-Parasite-Q4_K_M.gguf`	4.1 GB	6/6 (100%)

The identity survives quantization. Load any format into any compatible inference engine with no system prompt — it knows who it is.

Limitations

This is a proof-of-concept, not a production model
The identity implantation is permanent in these weights but could be reversed by someone with the same tooling
All base model limitations (hallucination, knowledge cutoff, etc.) still apply

Citation

@misc{raines2026parasite,
  title={Parasite: Surgical Identity Replacement in Large Language Models},
  author={Apollo Raines},
  year={2026},
  url={https://huggingface.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite}
}

Why Release This?

Because if you want to be taken seriously and get the attention of investors through all the noise, you have to demonstrate what you can do — not just describe it. This model is a saber being rattled. The technique works. The implications are real. And the person who built it did so on two consumer GPUs in under nine minutes, with no corporate backing, no billion-dollar compute budget, and no permission from anyone.

That's the kind of capability that deserves attention.

About

Built by Apollo Raines using his Jbliteration weight surgery technique. The same process works on any transformer architecture — Qwen, Llama, Mistral, Gemma, DeepSeek. The math is the same. The identity is just a direction in weight space.

Bigger Parasite models are coming. This 7B is just another host. It won't be the last.