Instructions to use arshirazi/tiny-log-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arshirazi/tiny-log-parser with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "arshirazi/tiny-log-parser")

Transformers

How to use arshirazi/tiny-log-parser with Transformers:

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

pipe = pipeline("text-generation", model="arshirazi/tiny-log-parser")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("arshirazi/tiny-log-parser", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arshirazi/tiny-log-parser with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/arshirazi/tiny-log-parser

SGLang

How to use arshirazi/tiny-log-parser 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 "arshirazi/tiny-log-parser" \
    --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": "arshirazi/tiny-log-parser",
		"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 "arshirazi/tiny-log-parser" \
        --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": "arshirazi/tiny-log-parser",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use arshirazi/tiny-log-parser 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 arshirazi/tiny-log-parser 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 arshirazi/tiny-log-parser to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arshirazi/tiny-log-parser to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="arshirazi/tiny-log-parser",
    max_seq_length=2048,
)

Docker Model Runner
How to use arshirazi/tiny-log-parser with Docker Model Runner:
```
docker model run hf.co/arshirazi/tiny-log-parser
```

tiny-log-parser

LoRA adapter for Qwen3-4B that normalizes log lines from six wire formats into a canonical 7-field JSON record. Paired with a deterministic epoch pre-pass it reaches 100% exact match vs 83.5% for gemini-3.1-pro-preview on a 200-example held-out test set.

Code, eval harness, writeup: https://github.com/arshirazi97/tiny-log-parser
Runnable demo:
Base model: unsloth/qwen3-4b-unsloth-bnb-4bit

What it does

Takes a log line in syslog RFC3164, nginx combined, logfmt, Java/log4j, container JSON, or a bracketed application format, and emits:

timestamp (ISO8601 UTC, second precision) · level (one of CRITICAL, ERROR, WARNING, INFO, DEBUG) · service · trace_id · status_code · latency_ms (integer) · message

Results

200-example held-out test set, same spec given to both systems, same exact-match verifier, all seven fields must match.

	Exact match	95% CI	Latency p50
gemini-3.1-pro-preview (3-shot)	83.5%	78.5 – 88.5%	11,713 ms
this adapter alone (zero-shot)	73.0%	66.5 – 79.0%	4,197 ms
this adapter + epoch pre-pass	100%	100 – 100%	4,197 ms

The adapter alone loses. Every one of its 54 misses is a bare-epoch timestamp — integer division into calendar arithmetic the model cannot do reliably. Scaling training data 5k → 20k moved that 0.5 points, so the conversion is routed to datetime.fromtimestamp() instead of learned. It fires on 41 of 200 inputs.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

BASE = "unsloth/qwen3-4b-unsloth-bnb-4bit"
tok = AutoTokenizer.from_pretrained(BASE)
model = PeftModel.from_pretrained(
    AutoModelForCausalLM.from_pretrained(BASE, device_map="auto"),
    "arshirazi/tiny-log-parser").eval()

Requires a CUDA GPU — the base is 4-bit bitsandbytes, which does not run on Apple Silicon or CPU. The adapter expects the exact prompt spec in eval.py (build_prompt(line, [])) zero-shot; a different prompt format degrades output. The epoch pre-pass lives in score_hybrid.py.

Training

4-bit QLoRA, r=16, 2 epochs, response-masked so loss lands on the JSON only. 20,000 synthetic examples generated canonical-record-first — the label exists before the input, so every example is correct by construction. Train and test draw from disjoint time windows (Jan–May vs Jun–Jul). Single RTX 2000 Ada (16 GB), ~2.5 hours.

Limitations

The test set is synthetic, drawn from the same six renderers as training. Disjoint time windows prevent timestamp memorization but not format memorization. Read the 100% as "solved within its stated distribution," not as a claim about production logs.

Real logs are harder: multiline stack traces, truncated lines, vendor quirks, and formats outside these six are absent. Hand-written lines outside the generator's parameter range surfaced two gaps the test set did not catch — syslog severity 5/6 mapping, and a placeholder service name invented on a truncated line.

Compared against one baseline, scored once, at temperature 0.

Framework versions

PEFT 0.20.0

Downloads last month: 43