Instructions to use neuracoder/neuracoder-tiny-1.1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neuracoder/neuracoder-tiny-1.1b with Transformers:

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

pipe = pipeline("text-generation", model="neuracoder/neuracoder-tiny-1.1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("neuracoder/neuracoder-tiny-1.1b")
model = AutoModelForMultimodalLM.from_pretrained("neuracoder/neuracoder-tiny-1.1b")
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 neuracoder/neuracoder-tiny-1.1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neuracoder/neuracoder-tiny-1.1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neuracoder/neuracoder-tiny-1.1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neuracoder/neuracoder-tiny-1.1b

SGLang

How to use neuracoder/neuracoder-tiny-1.1b 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 "neuracoder/neuracoder-tiny-1.1b" \
    --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": "neuracoder/neuracoder-tiny-1.1b",
		"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 "neuracoder/neuracoder-tiny-1.1b" \
        --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": "neuracoder/neuracoder-tiny-1.1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neuracoder/neuracoder-tiny-1.1b with Docker Model Runner:
```
docker model run hf.co/neuracoder/neuracoder-tiny-1.1b
```

neuracoder commited on 6 days ago

Commit

57bc5d9

verified ·

1 Parent(s): 0ddbd1a

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -38,6 +38,8 @@ metrics:
 Unlike giant models (7B+ parameters) that require professional GPUs and high memory, **Neuracoder-Tiny** runs easily on personal laptops, CPU‑only systems, single‑board computers (e.g., Raspberry Pi 4), and even smartphones (via conversion to ONNX or TensorFlow Lite). Although inspired by modern code generation architectures, it is completely independent, local, and optimized for real‑world developer needs.
 ---
 ## ✨ Key Features (Detailed)
@@ -73,7 +75,6 @@ Unlike giant models (7B+ parameters) that require professional GPUs and high mem
 ---
 ## 📊 Benchmarks & Comprehensive Evaluation
-![neuracoder-tiny-1.3b](https://huggingface.co/neuracoder/neuracoder-tiny-1.3b/resolve/main/neuracoder-tiny-1.3b.png)
 We evaluated Neuracoder-Tiny-1.3B on **three standard datasets**:
 1. **HumanEval** (OpenAI) – 164 Python programming problems, primary metric pass@1.

 Unlike giant models (7B+ parameters) that require professional GPUs and high memory, **Neuracoder-Tiny** runs easily on personal laptops, CPU‑only systems, single‑board computers (e.g., Raspberry Pi 4), and even smartphones (via conversion to ONNX or TensorFlow Lite). Although inspired by modern code generation architectures, it is completely independent, local, and optimized for real‑world developer needs.
+![neuracoder-tiny-1.3b](https://huggingface.co/neuracoder/neuracoder-tiny-1.3b/resolve/main/neuracoder-tiny-1.3b.png)
 ---
 ## ✨ Key Features (Detailed)
 ---
 ## 📊 Benchmarks & Comprehensive Evaluation
 We evaluated Neuracoder-Tiny-1.3B on **three standard datasets**:
 1. **HumanEval** (OpenAI) – 164 Python programming problems, primary metric pass@1.