Instructions to use dylanmurzello/redax-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dylanmurzello/redax-8b with Transformers:

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

pipe = pipeline("text-generation", model="dylanmurzello/redax-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dylanmurzello/redax-8b")
model = AutoModelForCausalLM.from_pretrained("dylanmurzello/redax-8b", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dylanmurzello/redax-8b 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 dylanmurzello/redax-8b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dylanmurzello/redax-8b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dylanmurzello/redax-8b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dylanmurzello/redax-8b: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 dylanmurzello/redax-8b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dylanmurzello/redax-8b: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 dylanmurzello/redax-8b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dylanmurzello/redax-8b:Q4_K_M

Use Docker

docker model run hf.co/dylanmurzello/redax-8b:Q4_K_M

LM Studio
Jan

vLLM

How to use dylanmurzello/redax-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dylanmurzello/redax-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dylanmurzello/redax-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dylanmurzello/redax-8b:Q4_K_M

SGLang

How to use dylanmurzello/redax-8b 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 "dylanmurzello/redax-8b" \
    --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": "dylanmurzello/redax-8b",
		"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 "dylanmurzello/redax-8b" \
        --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": "dylanmurzello/redax-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dylanmurzello/redax-8b with Ollama:
```
ollama run hf.co/dylanmurzello/redax-8b:Q4_K_M
```

Unsloth Studio

How to use dylanmurzello/redax-8b 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 dylanmurzello/redax-8b 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 dylanmurzello/redax-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dylanmurzello/redax-8b to start chatting

How to use dylanmurzello/redax-8b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dylanmurzello/redax-8b: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": "dylanmurzello/redax-8b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dylanmurzello/redax-8b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dylanmurzello/redax-8b: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 dylanmurzello/redax-8b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use dylanmurzello/redax-8b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dylanmurzello/redax-8b: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 "dylanmurzello/redax-8b: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 dylanmurzello/redax-8b with Docker Model Runner:
```
docker model run hf.co/dylanmurzello/redax-8b:Q4_K_M
```

Lemonade

How to use dylanmurzello/redax-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dylanmurzello/redax-8b:Q4_K_M

Run and chat with the model

lemonade run user.redax-8b-Q4_K_M

List all available models

lemonade list

redax-8b

Qwen3-8B fine-tuned to find personally identifying information in text and return the exact spans. Built as the LLM strategy of redax, a schema-driven de-identification engine.

Model Details

Developed by: Dylan Murzello
Model type: causal LM, full-parameter SFT for schema-conditioned span extraction
Language: English
License: Apache-2.0
Finetuned from: Qwen/Qwen3-8B

file	what
`model.safetensors`	bf16 reference weights
`redax-8b-Q4_K_M.gguf`	5 GB, runs on a laptop
`redax-8b-Q8_0.gguf`	8.7 GB, near-lossless

Uses

The system prompt names a schema: the labels to find and guard rules for lookalikes that must be left alone. The model reads the input text and returns a JSON array of {"text": ..., "label": ...} objects — substrings copied character-for-character, nothing rewritten. When nothing qualifies it answers [], and it means it: roughly a fifth of the training data is traps (clinical values, order numbers, codes that look sensitive and are not).

Out-of-scope: this is not a compliance tool. It will miss spans sometimes, and de-identification regulations (HIPAA, GDPR) are standards a model cannot certify on its own — keep a human, or at least an ensemble with pattern matching, in the loop for anything real. English only. Not for re-identification of individuals.

How to Get Started

ollama pull huggingface.co/dylanmurzello/redax-8b:Q4_K_M

One quirk: output opens with an empty <think></think> block (Qwen3 training-template artifact). Strip it, then parse the JSON.

Training Details

53,141 schema-conditioned examples (clinical / financial / general PII), mixed from public corpora (Nemotron-PII, Gretel) plus targeted synthetic generation, deduped and 8-gram-decontaminated against the eval benchmark.


method	full-parameter SFT (TRL 1.9, assistant-only loss)
epochs	2 (824 steps, packed 2048 ctx, effective batch 32)
lr	1e-5, cosine
precision	bf16
final eval loss	0.0185, no train/eval gap

Evaluation

Benchmark rows (strict/relaxed span F1, hard-negative false positives, privacy leak rate) get added here once the eval suite has run — including the Q4_K_M vs Q8_0 quantization delta.

Environmental Impact

One evening on a single rented H100 (~2.5 GPU-hours). The whole fine-tune cost about as much as a burrito.

Downloads last month: 61

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for dylanmurzello/redax-8b

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(357)

this model

Quantizations

1 model