Instructions to use davidr99/qwen35-address-std with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidr99/qwen35-address-std with Transformers:

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

pipe = pipeline("text-generation", model="davidr99/qwen35-address-std")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("davidr99/qwen35-address-std")
model = AutoModelForMultimodalLM.from_pretrained("davidr99/qwen35-address-std")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use davidr99/qwen35-address-std with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="davidr99/qwen35-address-std",
	filename="Qwen35-Address-Std-2B-BF16.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 davidr99/qwen35-address-std 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 davidr99/qwen35-address-std:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf davidr99/qwen35-address-std:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf davidr99/qwen35-address-std:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf davidr99/qwen35-address-std: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 davidr99/qwen35-address-std:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf davidr99/qwen35-address-std: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 davidr99/qwen35-address-std:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf davidr99/qwen35-address-std:Q4_K_M

Use Docker

docker model run hf.co/davidr99/qwen35-address-std:Q4_K_M

LM Studio
Jan

vLLM

How to use davidr99/qwen35-address-std with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidr99/qwen35-address-std"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidr99/qwen35-address-std",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davidr99/qwen35-address-std:Q4_K_M

SGLang

How to use davidr99/qwen35-address-std 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 "davidr99/qwen35-address-std" \
    --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": "davidr99/qwen35-address-std",
		"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 "davidr99/qwen35-address-std" \
        --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": "davidr99/qwen35-address-std",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use davidr99/qwen35-address-std with Ollama:
```
ollama run hf.co/davidr99/qwen35-address-std:Q4_K_M
```

Unsloth Studio

How to use davidr99/qwen35-address-std 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 davidr99/qwen35-address-std 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 davidr99/qwen35-address-std to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for davidr99/qwen35-address-std to start chatting

How to use davidr99/qwen35-address-std with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf davidr99/qwen35-address-std: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": "davidr99/qwen35-address-std:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use davidr99/qwen35-address-std with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf davidr99/qwen35-address-std: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 davidr99/qwen35-address-std:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use davidr99/qwen35-address-std with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf davidr99/qwen35-address-std: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 "davidr99/qwen35-address-std: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 davidr99/qwen35-address-std with Docker Model Runner:
```
docker model run hf.co/davidr99/qwen35-address-std:Q4_K_M
```

Lemonade

How to use davidr99/qwen35-address-std with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull davidr99/qwen35-address-std:Q4_K_M

Run and chat with the model

lemonade run user.qwen35-address-std-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

qwen35-address-std (2B, v1)

Superseded by davidr99/qwen35-address-std-4B-v5 (99.2% exact-match, no city-spelling drift, trimmed output). This repo is kept for A/B comparison.

Qwen3.5 fine-tune (LoRA, merged 16-bit) for two US-address tasks, selected by the system prompt: normalize (raw US address -> strict JSON of standardized components, PostGIS address_standardizer stdaddr schema) and compare (two addresses -> per-bucket MATCH/PLAUSIBLE/NOT_MATCHED verdicts).

Trained on dataset revision v1 (pinned tag on both datasets above).

Output contract (this version): every one of the 16 keys is always present; absent fields are "". (v5+ models switched to omitting empty keys.)

This version (v1): the original release. Baseline street-suffix set (21 types); the prompt predates the spelling-preservation and city-disambiguation rules added in v2. GGUF builds are included under gguf/.

Results

Development-harness measurements (~760-row v1 val): normalize exact-match ~98.8-98.9%, compare ~99.5%. Known weakness: occasionally altered the spelling of rare city names (e.g. BUTLER->BATALER) -- the motivation for the v2+ data work.

Version history

Model	Data	Normalize exact-match	Notes
2B (v1, `qwen35-address-std`)	v1	~98.9%*	first release; *dev harness, ~760-row val
2B-v2	v2	98.0%	USPS suffixes + prompt rules; 761-row val
2B-v3	v3	94.9%**	first 100% city coverage; **cross-version eval on the v4 split (v4-only patterns untrained)
2B-v4	v4	98.8%	PostGIS-grammar patterns; 2,139-row val
4B-v4	v4	99.3%	first 4B; city-spelling garbles eliminated
2B-v5	v5	98.6%	trimmed JSON (43% fewer output tokens); fastest
4B-v5 (current)	v5	99.2%	garble-free + trimmed output -- recommended

Normalize system prompt (verbatim, as trained)

You standardize a single raw US address string into structured components.
Return ONLY a JSON object with these exact keys (always include every key; use "" when absent):
  building, houseNum, predir, qual, pretype, name, suftype, sufdir,
  ruralRoute, extra, city, state, country, zipcode, box, unit

Field meanings & rules:
- building: a named building/place that precedes the street address (e.g. "EMPIRE STATE BUILDING").
- houseNum: the primary street number.
- predir: directional BEFORE the street name (N, S, E, W, NE, NW, SE, SW).
- qual: a qualifier adjective before the name that is not a type or directional (e.g. "OLD", "NEW").
- pretype: street type or route descriptor BEFORE the name (e.g. "AVE", "US RTE", "STATE RTE").
- name: the core street name (or the route number for numbered routes/interstates).
- suftype: street type AFTER the name (e.g. "ST", "RD", "AVE", "BLVD").
- sufdir: directional AFTER the street (post-directional), e.g. "NW" in "Pennsylvania Ave NW".
- ruralRoute: the rural route NUMBER only (e.g. "2" for "RR 2", "1" for "HC 1").
- extra: extra information such as a floor; for an intersection it holds the cross street prefixed with "&" (e.g. "& 5TH AVE").
- city / state / zipcode: the locality, 2-letter state, and ZIP.
- country: always "USA".
- box: a post-office / route box, normalized to "BOX <number>" (e.g. "BOX 152"); drop any "PO"/"P.O." prefix.
- unit: secondary unit (e.g. "APT 5B", "STE 200"), OR any leftover token trailing the street type.

Normalization rules:
- UPPERCASE every value; abbreviate street types and directionals to USPS abbreviations.
- "St"/"Saint" before a name is part of the name ("ST CHARLES"), not the type "ST".
- street type before the name -> pretype; after the name -> suftype.
- directional AFTER the street (and after the suftype) -> sufdir (e.g. "NW" in "Pennsylvania Ave NW").
- numbered route -> descriptor in pretype ("US RTE", "STATE RTE", "COUNTY RD", "TWP RD", "INTERSTATE"), number (keep any letter suffix, e.g. "75A") in name.
- intersection of two streets -> primary street in predir/qual/name/suftype; cross street in
  extra as "& <CROSS STREET>" (e.g. "& 5TH AVE"); houseNum stays empty.
- any leftover token trailing the street type -> unit (whatever it is).
- zipcode may include a ZIP+4 suffix (e.g. "44646-1234"); keep it if present, else use the 5-digit ZIP or "".
- country is always "USA"; output the JSON object only.

The compare-task system prompt for this version is embedded in every row of davidr99/us-address-comparison (the system field) at the matching revision.

Usage

See the usage snippet on the current release's card -- identical apart from the repo name (greedy decoding, enable_thinking=False, use the inner text tokenizer of the multimodal processor). eval_address_model.ipynb in this repo family scores any version against any dataset tag.

Downloads last month: 123

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for davidr99/qwen35-address-std

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

unsloth/Qwen3.5-2B

Adapter

(31)

this model

davidr99
/

qwen35-address-std

You need to agree to share your contact information to access this model

qwen35-address-std (2B, v1)

Results

Version history

Normalize system prompt (verbatim, as trained)

Usage

Model tree for davidr99/qwen35-address-std

Datasets used to train davidr99/qwen35-address-std