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

ff59bb3

verified ·

1 Parent(s): 083dd6f

Add code-model baselines, confidence intervals, and paired test

Browse files

Files changed (1) hide show

README.md +50 -17

README.md CHANGED Viewed

@@ -12,11 +12,9 @@ pipeline_tag: text-generation
 # kernel-coder-1.5b
-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
@@ -41,23 +39,58 @@ 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.
-## 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)

 # kernel-coder-1.5b
+A 1.5B code model that writes **C in Linux kernel style** — tab indentation,
+brace placement, declarations before statements, `-ERRNO` returns, `goto` label
+unwinding — while keeping the base model's Python ability.
 ## Usage
 Chat template ships with the tokenizer. Greedy decoding; the answer is the last
 fenced code block.
+## Results — kernel C style
+**N = 40** held-out kernel-doc tasks, greedy decoding, scored with the kernel's
+own `scripts/checkpatch.pl --no-tree --file --strict`, reported as weighted
+defects per line: `(2*errors + warnings + 0.5*checks) / lines`. All models were
+given the identical prompts and scored by identical code.
+| | params | defects / line ↓ | 95% CI | checkpatch errors ↓ | idiom ↑ |
+|---|---|---|---|---|---|
+| deepseek-coder-1.3b-instruct | 1.3B | 0.679 | ±0.196 | 4.43 | 0.738 |
+| Qwen2.5-Coder-3B-Instruct | 3B | 0.750 | ±0.182 | 4.78 | 0.755 |
+| Qwen2.5-Coder-1.5B-Instruct *(base)* | 1.5B | 0.872 | ±0.185 | 5.58 | 0.664 |
+| **kernel-coder-1.5b** | **1.5B** | **0.020** | **±0.012** | **0.00** | **0.995** |
+| *the kernel's own code* | — | *0.017* | — | *0.00* | *1.000* |
+Against `Qwen2.5-Coder-3B-Instruct` — twice the parameters — the paired
+difference is **−0.73 defects/line**, 95% CI [−0.91, −0.55], t = −7.87, lower on
+**33 of 40** tasks. No general-purpose code model tested comes close, and this
+model sits within noise of the kernel's own source.
+## Results — Python
+MBPP `test`, 200 problems, greedy, executing the dataset's assertions.
+| | params | pass@1 |
 |---|---|---|
+| deepseek-coder-1.3b-instruct | 1.3B | 0.250 |
+| **kernel-coder-1.5b** | 1.5B | **0.420** |
+| Qwen2.5-Coder-1.5B-Instruct *(base)* | 1.5B | 0.420 |
+| Qwen2.5-Coder-3B-Instruct | 3B | 0.535 |
+Python is unchanged from base — the kernel specialisation cost nothing, and
+gained nothing, here. A 3B model is still better at general Python.
+If you re-run MBPP, strip the trailing `print(...)` / `assert` / `__main__`
+statements the model appends after the function before executing. They run at
+import time and abort otherwise-correct solutions; leaving them in costs roughly
+3 points.
+## Limitations
+- **The kernel gains are stylistic and structural, not functional.** Kernel code
+  cannot be executed in a sandbox, so nothing here measures semantic
+  correctness. A well-formatted stub and a working implementation score alike.
+  Review output before use.
+- **A large share of the checkpatch improvement is indentation.** The base model
+  indents kernel C with spaces; this one uses tabs, and checkpatch flags every
+  space-indented line.
+- **Roughly half of kernel completions** leave part of the body as placeholder
+  comments rather than a full implementation — a rate unchanged from base.
+- **N = 40** on the kernel evaluation. The margin over the baselines is large
+  relative to that, but finer distinctions would need a bigger set.
+- Training methodology is not published.
 Base model: [`Qwen/Qwen2.5-Coder-1.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)