Instructions to use smoky1496/SpawnPoint-Coder-7B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smoky1496/SpawnPoint-Coder-7B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="smoky1496/SpawnPoint-Coder-7B-AWQ")
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("smoky1496/SpawnPoint-Coder-7B-AWQ")
model = AutoModelForCausalLM.from_pretrained("smoky1496/SpawnPoint-Coder-7B-AWQ", 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 smoky1496/SpawnPoint-Coder-7B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smoky1496/SpawnPoint-Coder-7B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smoky1496/SpawnPoint-Coder-7B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smoky1496/SpawnPoint-Coder-7B-AWQ

SGLang

How to use smoky1496/SpawnPoint-Coder-7B-AWQ 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 "smoky1496/SpawnPoint-Coder-7B-AWQ" \
    --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": "smoky1496/SpawnPoint-Coder-7B-AWQ",
		"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 "smoky1496/SpawnPoint-Coder-7B-AWQ" \
        --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": "smoky1496/SpawnPoint-Coder-7B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use smoky1496/SpawnPoint-Coder-7B-AWQ with Docker Model Runner:
```
docker model run hf.co/smoky1496/SpawnPoint-Coder-7B-AWQ
```

SpawnPoint-Coder-7B-AWQ / README.md

smoky1496

SpawnPoint-Coder-7B v5: side-scrolling shooters, per-genre format, reads Vietnamese directly

75aed62 verified about 9 hours ago

preview code

Raw History Blame Contribute Delete

4.75 kB

	---
	license: apache-2.0
	language: [en, vi]
	library_name: transformers
	tags: [gamedev, godot, json, spawn-point, awq]
	---

	# SpawnPoint-Coder-7B

	A 7B model that generates Godot 4 games. Fine-tuned for [Spawn Point](https://github.com/leluong141996-dev/Spawn-Point),
	an open-source autonomous game studio: you describe a game in plain English or Vietnamese, the model writes
	the game design as strict JSON, and Spawn Point compiles it into a playable Godot 4 project (scenes, GDScript
	components, levels, sprites) that runs on desktop or in the browser.

	What it does inside the pipeline:

	- Design: game idea → the game's design (one small schema per genre: character, abilities, enemies, goal, art style, feel).
	- Tweak: "jump 20% higher, add a sword, make it cartoon" → a precise patch of the game.
	- Edit an entity: "double its health and make it shoot fireballs" → component and parameter changes.

	4-bit AWQ, runs on a single 12 GB GPU.

	What's new in v5
	- Side-scrolling shooters ("a falcon ship fights drones and saucers, the boss is a mothership"): enemies that
	fly straight, in waves, dive at you or stop and shoot; power-ups; a boss.
	- Vietnamese is read directly: no separate translation step, so names come out right ("chú vịt" is a Duck).
	- One small schema per genre: shorter answers and prompts (a third of the v4 prompt) and no cross-genre
	mistakes such as a rescue target in a farm.
	- Fixes from v4: "a wizard shooting skeletons" keeps the shoot ability, "collect coins" is a collect goal, an unnamed
	pickup is a Coin.

	Needs Spawn Point 0.3 or later: v5 answers in the per-genre format. Older Spawn Point versions expect the v4
	format; use release `v4-release` of this repo with them.

	## Run it

	```bash
	docker run --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:v0.10.2 \
	--model smoky1496/SpawnPoint-Coder-7B-AWQ --served-model-name SpawnPoint-Coder-7B --max-model-len 16384 --gpu-memory-utilization 0.85
	```

	Then Spawn Point finds it automatically at `http://localhost:8000/v1`.

	## Evaluation

	Hand-written prompts in English and Vietnamese through the whole pipeline, same server and sampling for both versions.
	Sealed sets were written before training and not looked at until the release decision. The first two rows include
	prompts about the genre v4 did not know, so v4 cannot be expected to answer them.

	\| benchmark (prompts fully right) \| v4 \| v5 (this release) \|
	\|---\|---\|---\|
	\| sealed set: shooters and the v4 fixes (16 prompts) \| 56% \| 88% \|
	\| dev set: shooters and the v4 fixes (24 prompts) \| 54% \| 83% \|
	\| sealed set: farms, tower defense, cartoon (12 prompts) \| 67% \| 92% \|
	\| 16 prompts: farms, tower defense, melee, cartoon \| 75% \| 75% \|
	\| sealed set: the first nine genres (12 prompts) \| 67% \| 58% \|
	\| 30 human-written prompts \| 87% \| 80% \|
	\| 12 prompts: bubble, rescue, survivor \| 92% \| 92% \|

	Where v5 is a little behind v4: on the 30 prompts and the sealed set written before shooters and farms existed.
	Some of those prompts are now genuinely ambiguous ("a space shooter" can be a side-scrolling shooter, "a farm game"
	a farming game), and a few name the player only indirectly ("a tank shooting monsters": the tank can come out as the
	default hero). Results vary by one to three prompts per set from run to run. A patch for this is planned.

	Held-out synthetic examples with one exact answer (v5 only: they use the v5 format): briefs 73%, tweaks 98%, entity edits 100%.

	The 4-bit AWQ files you download, measured the same way:

	\| benchmark (prompts fully right) \| AWQ build \|
	\|---\|---\|
	\| sealed set: shooters and the v4 fixes (16 prompts) \| 75% \|
	\| 30 human-written prompts \| 77% \|
	\| dev set: shooters and the v4 fixes (24 prompts) \| 83% \|

	## Limitations

	- Fine-tuned only for the 2D game kinds Spawn Point builds: **platformers (including rescue missions and sword
	fighting), top-down arenas and survivors, bubble shooters, farming games, tower defense and side-scrolling
	shooters**. Other genres (3D, RPG systems, card games, racing…) and free-form Godot coding were not part of the
	training data, so expect results no better than a general 7B coder model there.
	- Prompts that do not say the genre can be read either way ("a space shooter" may come out as a side-scrolling
	shooter, "a farm game" as a farming game).
	- It writes Spawn Point's JSON formats; the GDScript itself comes from Spawn Point's tested component
	library, not from the model. Outside Spawn Point it is a general coding model with a narrow specialty.
	- Occasionally one detail of a request is missed (an enemy's name, a palette); Spawn Point's validator and
	normalizer catch most of these.

	## License

	Apache 2.0, see `LICENSE` and `NOTICE`.