Instructions to use logcat-ai/safelog-lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use logcat-ai/safelog-lm with Transformers:

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

pipe = pipeline("text-generation", model="logcat-ai/safelog-lm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("logcat-ai/safelog-lm")
model = AutoModelForCausalLM.from_pretrained("logcat-ai/safelog-lm", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use logcat-ai/safelog-lm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/logcat-ai/safelog-lm

SGLang

How to use logcat-ai/safelog-lm 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 "logcat-ai/safelog-lm" \
    --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": "logcat-ai/safelog-lm",
		"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 "logcat-ai/safelog-lm" \
        --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": "logcat-ai/safelog-lm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use logcat-ai/safelog-lm with Docker Model Runner:
```
docker model run hf.co/logcat-ai/safelog-lm
```

SafeLog-LM

A fine-tuned Gemma 3 270M model specialized in redacting Personally Identifiable Information (PII) from Android system logs (logcat, bugreports, dmesg).

Model Details

Base Model: google/gemma-3-270m-it
Task: PII Redaction
Domain: Android system logs
Parameters: 270M
Training: QLoRA fine-tuning with completion-only loss masking

Supported PII Types

Category	Tags
Device IDs	`[IMEI]`, `[SERIAL_NUMBER]`, `[ANDROID_ID]`, `[ADVERTISING_ID]`, `[MAC_ADDRESS]`, `[ICCID]`, `[IMSI]`
Network/Location	`[IP_ADDRESS]`, `[GPS_COORDINATES]`, `[WIFI_SSID]`, `[BLUETOOTH_NAME]`
Personal Info	`[PERSON_NAME]`, `[EMAIL]`, `[PHONE_NUMBER]`, `[ACCOUNT_NAME]`
Paths	`[PATH_USERNAME]`
Secrets	`[ACCESS_TOKEN]`, `[CERTIFICATE_FINGERPRINT]`
URLs	`[URL_WITH_PII]`

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "logcat-ai/safelog-lm"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)

SYSTEM_PROMPT = (
    "You are a PII redaction tool. Replace all personally identifiable information "
    "in the input text with the appropriate tag. Preserve all other text exactly. "
    "Tags: [IMEI], [SERIAL_NUMBER], [ANDROID_ID], [ADVERTISING_ID], [MAC_ADDRESS], "
    "[ICCID], [IMSI], [IP_ADDRESS], [GPS_COORDINATES], [WIFI_SSID], [BLUETOOTH_NAME], "
    "[PERSON_NAME], [EMAIL], [PHONE_NUMBER], [ACCOUNT_NAME], [PATH_USERNAME], "
    "[ACCESS_TOKEN], [CERTIFICATE_FINGERPRINT], [URL_WITH_PII]"
)

def redact(text):
    prompt = f"""<start_of_turn>user
{SYSTEM_PROMPT}

Input: {text}<end_of_turn>
<start_of_turn>model
"""
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
    return tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip()

# Example
log_line = "I/TelephonyManager: getDeviceId() returning 358673091234567"
print(redact(log_line))
# Output: I/TelephonyManager: getDeviceId() returning [IMEI]

Examples

Input	Output
`D/Telephony: Sending SMS to +917514605529`	`D/Telephony: Sending SMS to [PHONE_NUMBER]`
`D/WifiService: Connected to SSID "Varun's Home 5G" with MAC aa:bb:cc:dd:ee:ff`	`D/WifiService: Connected to SSID "[WIFI_SSID]" with MAC [MAC_ADDRESS]`
`W/Auth: Bearer token=eyJhbGciOiJIUzI1...`	`W/Auth: Bearer token=[ACCESS_TOKEN]`
`I/SyncService: Syncing user priya@company.com from IP 192.168.1.105`	`I/SyncService: Syncing user [EMAIL] from IP [IP_ADDRESS]`
`D/ActivityManager: Process com.app started`	`D/ActivityManager: Process com.app started` (no PII)

Training Details

Dataset: ~1,770 examples (real Android logs + synthetic data)
Epochs: 5
Method: QLoRA (r=32, alpha=64)
Loss: Completion-only (prompt masked)
Final eval accuracy: 99.7%

Limitations

Optimized for Android log formats; may not generalize perfectly to other log types
Very long log lines (>512 tokens) may be truncated
Some PII categories have fewer training examples than others