Instructions to use Pinkstack/Luau-coder-v2-3B-base-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/Luau-coder-v2-3B-base-32k with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/Luau-coder-v2-3B-base-32k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstack/Luau-coder-v2-3B-base-32k")
model = AutoModelForCausalLM.from_pretrained("Pinkstack/Luau-coder-v2-3B-base-32k")
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

vLLM

How to use Pinkstack/Luau-coder-v2-3B-base-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/Luau-coder-v2-3B-base-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pinkstack/Luau-coder-v2-3B-base-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/Luau-coder-v2-3B-base-32k

SGLang

How to use Pinkstack/Luau-coder-v2-3B-base-32k 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 "Pinkstack/Luau-coder-v2-3B-base-32k" \
    --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": "Pinkstack/Luau-coder-v2-3B-base-32k",
		"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 "Pinkstack/Luau-coder-v2-3B-base-32k" \
        --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": "Pinkstack/Luau-coder-v2-3B-base-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Pinkstack/Luau-coder-v2-3B-base-32k 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 Pinkstack/Luau-coder-v2-3B-base-32k 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 Pinkstack/Luau-coder-v2-3B-base-32k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Pinkstack/Luau-coder-v2-3B-base-32k to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Pinkstack/Luau-coder-v2-3B-base-32k",
    max_seq_length=2048,
)

Docker Model Runner
How to use Pinkstack/Luau-coder-v2-3B-base-32k with Docker Model Runner:
```
docker model run hf.co/Pinkstack/Luau-coder-v2-3B-base-32k
```

Pinkstack commited on Jul 23, 2025

Commit

0839086

verified ·

1 Parent(s): 0e6314f

fixed issues and made fine-tuning easier

Browse files

modified model max length & added chat template even though the model is not for chat.

Files changed (1) hide show

tokenizer_config.json +3 -2

tokenizer_config.json CHANGED Viewed

@@ -179,10 +179,11 @@
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|pad|>",
   "padding_side": "right",
   "tokenizer_class": "GPT2Tokenizer",

     }
   },
   "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>' + message['content'] + '' }}{% elif message['role'] == 'user' %}{{ '<|user|>' + message['content'] + '' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>' + message['content'] + eos_token + '' }}{% else %}{{ '<|assistant|>' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
   "pad_token": "<|pad|>",
   "padding_side": "right",
   "tokenizer_class": "GPT2Tokenizer",