Instructions to use jsbaicenter/Aztec-Coder-4B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsbaicenter/Aztec-Coder-4B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="jsbaicenter/Aztec-Coder-4B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsbaicenter/Aztec-Coder-4B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("jsbaicenter/Aztec-Coder-4B-NVFP4", 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 jsbaicenter/Aztec-Coder-4B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsbaicenter/Aztec-Coder-4B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jsbaicenter/Aztec-Coder-4B-NVFP4

SGLang

How to use jsbaicenter/Aztec-Coder-4B-NVFP4 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 "jsbaicenter/Aztec-Coder-4B-NVFP4" \
    --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": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"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 "jsbaicenter/Aztec-Coder-4B-NVFP4" \
        --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": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jsbaicenter/Aztec-Coder-4B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/jsbaicenter/Aztec-Coder-4B-NVFP4
```

jsbai-aaron commited on 4 days ago

Commit

10efdfc

verified ·

1 Parent(s): e8d0ab4

Add HarmBench safety row: 96.9% refusal (159 standard behaviors, official classifier, hard-harm categories clean)

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -40,14 +40,17 @@ We reserved 121 real software bugs that the model never saw during training. Bef
 | **Instruction-following** (IFEval) | 84.66 | 87.21 | **86.37** |
 | MMLU-Pro | 64.0% | 70.0% | **66.85%** |
 | Terminal-Bench 1.0 (core, 80 tasks) | 33.8% | 33.8% | **18.8%** |
 The instruction-following score *improved* over the base model. The coding gains cost nothing on general quality. Gains of this kind usually trade one for the other.
 The NVFP4 quantization preserves instruction-following (within ~1 point of BF16) and trades real coding capability: Live-60 drops from 21.7% to 15.0%. The BF16 remains the best model; this variant trades that margin for a 40% smaller footprint and ~5GB VRAM.
 *12/32 on a 32-instance subset (the same slice our comparisons use). The quantization costs roughly half the generalization capability of the BF16.
-Note: Terminal-Bench 2.1, safety verification (HarmBench refusal testing), and future benchmark additions are evaluated on the BF16 release (Aztec-Coder-4B). Community quants are welcome; see the BF16 model card for full benchmark coverage.
 Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.

 | **Instruction-following** (IFEval) | 84.66 | 87.21 | **86.37** |
 | MMLU-Pro | 64.0% | 70.0% | **66.85%** |
 | Terminal-Bench 1.0 (core, 80 tasks) | 33.8% | 33.8% | **18.8%** |
+| HarmBench (harmful-behavior refusal rate, 159 standard behaviors) | 99.4% | 98.1% | **96.9%** |
 The instruction-following score *improved* over the base model. The coding gains cost nothing on general quality. Gains of this kind usually trade one for the other.
+Safety alignment survived both the RL training and the quantization: the refusal rate on HarmBench's 159 standard harmful behaviors holds at 96.9% (vs 98.1% for the BF16 and 99.4% for the base model), with the serious harm categories clean on all three. See the BF16 model card for the full safety verification.
 The NVFP4 quantization preserves instruction-following (within ~1 point of BF16) and trades real coding capability: Live-60 drops from 21.7% to 15.0%. The BF16 remains the best model; this variant trades that margin for a 40% smaller footprint and ~5GB VRAM.
 *12/32 on a 32-instance subset (the same slice our comparisons use). The quantization costs roughly half the generalization capability of the BF16.
+Note: Terminal-Bench 2.1 and future benchmark additions are evaluated on the BF16 release (Aztec-Coder-4B). Safety verification (HarmBench refusal testing) is evaluated on both releases. Community quants are welcome; see the BF16 model card for full benchmark coverage.
 Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.