Instructions to use nethunter2023/kernel-coder-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nethunter2023/kernel-coder-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="nethunter2023/kernel-coder-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nethunter2023/kernel-coder-1.5b")
model = AutoModelForCausalLM.from_pretrained("nethunter2023/kernel-coder-1.5b", 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 nethunter2023/kernel-coder-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nethunter2023/kernel-coder-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nethunter2023/kernel-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nethunter2023/kernel-coder-1.5b

SGLang

How to use nethunter2023/kernel-coder-1.5b 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 "nethunter2023/kernel-coder-1.5b" \
    --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": "nethunter2023/kernel-coder-1.5b",
		"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 "nethunter2023/kernel-coder-1.5b" \
        --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": "nethunter2023/kernel-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nethunter2023/kernel-coder-1.5b with Docker Model Runner:
```
docker model run hf.co/nethunter2023/kernel-coder-1.5b
```

nethunter2023 commited on 5 days ago

Commit

083dd6f

verified ·

1 Parent(s): 91388be

results, no methodology

Browse files

Files changed (1) hide show

README.md +26 -1

README.md CHANGED Viewed

@@ -14,6 +14,12 @@ pipeline_tag: text-generation
 A 1.5B code model for writing **C in Linux kernel style**, and Python.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -33,6 +39,25 @@ print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
 ```
 Chat template ships with the tokenizer. Greedy decoding; the answer is the last
-fenced code block in the response.
 Base model: [`Qwen/Qwen2.5-Coder-1.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)

 A 1.5B code model for writing **C in Linux kernel style**, and Python.
+Given a description and a signature it produces kernel C following the
+conventions enforced in kernel review: tab indentation, brace placement,
+declarations before statements, `-ERRNO` returns, and `goto` label unwinding.
+## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 ```
 Chat template ships with the tokenizer. Greedy decoding; the answer is the last
+fenced code block.
+## Results
+Kernel C style, measured with the kernel's own `checkpatch.pl` on 40 held-out
+tasks. `reference` is the kernel's own implementation of the same functions.
+| | base | this model | reference |
+|---|---|---|---|
+| checkpatch defects / line ↓ | 0.872 | **0.020** | 0.017 |
+| checkpatch errors, mean ↓ | 5.58 | **0.00** | 0.00 |
+| style score ↑ | 0.211 | **0.968** | 0.977 |
+Python, MBPP test (200 problems):
+| | base | this model |
+|---|---|---|
+| pass@1 | 0.420 | 0.420 |
+The kernel-side gains are stylistic; Python correctness is unchanged from base.
 Base model: [`Qwen/Qwen2.5-Coder-1.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)