Instructions to use CodeStrux-Tech/tac-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeStrux-Tech/tac-1 with Transformers:

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

pipe = pipeline("text-generation", model="CodeStrux-Tech/tac-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeStrux-Tech/tac-1")
model = AutoModelForCausalLM.from_pretrained("CodeStrux-Tech/tac-1", 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

vLLM

How to use CodeStrux-Tech/tac-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeStrux-Tech/tac-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeStrux-Tech/tac-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CodeStrux-Tech/tac-1

SGLang

How to use CodeStrux-Tech/tac-1 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 "CodeStrux-Tech/tac-1" \
    --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": "CodeStrux-Tech/tac-1",
		"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 "CodeStrux-Tech/tac-1" \
        --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": "CodeStrux-Tech/tac-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CodeStrux-Tech/tac-1 with Docker Model Runner:
```
docker model run hf.co/CodeStrux-Tech/tac-1
```

Araya2001 commited on 29 days ago

Commit

5ff25af

verified ·

1 Parent(s): 75cce10

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -17,11 +17,11 @@ tags:
 ## What is tac-1
-Costa Rica has no street-address system. Addresses are reference-point narratives — "del antiguo higuerón de San Pedro, 100 metros sur" or "de la esquina noroeste del Mercado Central, 200 metros norte, casa esquinera." tac-1 parses these into a structured, leg-based JSON record. It performs **parsing only**: geometry (resolving the anchor point to coordinates and walking the OSM street graph along each leg) belongs to the deterministic grounder in the tico-address repo (`https://github.com/CodeStrux/tac-1`).
 ## Architecture
-tac-1 is a hybrid system. This model extracts the structured address fields (anchor name, anchor type, and a list of legs with direction and distance). The `tico` package then grounds the parse by walking the OSM street graph — it resolves the anchor to a coordinate via `resolve_anchor`, then traces each leg along the graph using the same geometry core that generated the training data. See `https://github.com/CodeStrux/tac-1` for the full grounder implementation.
 ## Evaluation
@@ -104,6 +104,5 @@ Contains information from OpenStreetMap (https://www.openstreetmap.org/copyright
 - [`CodeStrux-Tech/tac-1-gguf`](https://huggingface.co/CodeStrux-Tech/tac-1-gguf) — GGUF (Q5_K_M + f16) for llama.cpp / Ollama
 - [`CodeStrux-Tech/tac-1-lora`](https://huggingface.co/CodeStrux-Tech/tac-1-lora) — QLoRA adapter weights
 - [`CodeStrux-Tech/tac-1-corpus`](https://huggingface.co/CodeStrux-Tech/tac-1-corpus) — training corpus (ODbL)
-- Source code: `https://github.com/CodeStrux/tac-1`
 tac-1 is a derivative work of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Copyright 2024 Alibaba Cloud, licensed under the Apache License, Version 2.0. The upstream LICENSE is included in this repository.

 ## What is tac-1
+Costa Rica has no street-address system. Addresses are reference-point narratives — "del antiguo higuerón de San Pedro, 100 metros sur" or "de la esquina noroeste del Mercado Central, 200 metros norte, casa esquinera." tac-1 parses these into a structured, leg-based JSON record. It performs **parsing only**: geometry (resolving the anchor point to coordinates and walking the OSM street graph along each leg) belongs to a separate deterministic grounder (the companion `tico` package, not part of this model release).
 ## Architecture
+tac-1 is a hybrid system. This model extracts the structured address fields (anchor name, anchor type, and a list of legs with direction and distance). The `tico` package then grounds the parse by walking the OSM street graph — it resolves the anchor to a coordinate via `resolve_anchor`, then traces each leg along the graph using the same geometry core that generated the training data.
 ## Evaluation
 - [`CodeStrux-Tech/tac-1-gguf`](https://huggingface.co/CodeStrux-Tech/tac-1-gguf) — GGUF (Q5_K_M + f16) for llama.cpp / Ollama
 - [`CodeStrux-Tech/tac-1-lora`](https://huggingface.co/CodeStrux-Tech/tac-1-lora) — QLoRA adapter weights
 - [`CodeStrux-Tech/tac-1-corpus`](https://huggingface.co/CodeStrux-Tech/tac-1-corpus) — training corpus (ODbL)
 tac-1 is a derivative work of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Copyright 2024 Alibaba Cloud, licensed under the Apache License, Version 2.0. The upstream LICENSE is included in this repository.