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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsbaicenter/JSBAI-Coder-4B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("jsbaicenter/JSBAI-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

jsbai-aaron commited on about 1 month ago

Commit

9456c32

verified ·

1 Parent(s): 9a09467

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ We reserved 121 real software bugs that the model never saw during training. Bef
 | Benchmark | Qwen3.5-4B (base) | JSBAI-Coder-4B (BF16) | **JSBAI-Coder-4B-NVFP4** |
 |---|---|---|---|
-| **Generalization test** (121 unseen bugs, tests run to verify) | 10.1% | 82.9% | coming soon |
 | **Live-60** (60 real-world engineering tasks, solved end-to-end in containers) | 15.0% | 21.7% | **15.0%** |
 | **Instruction-following** (IFEval) | 84.66 | 87.21 | **86.37** |
 | MMLU-Pro | 64.0% | 70.0% | **66.85%** |
@@ -49,6 +49,8 @@ The instruction-following score *improved* over the base model. The coding gains
 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.
 Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.
 ## What it does

 | Benchmark | Qwen3.5-4B (base) | JSBAI-Coder-4B (BF16) | **JSBAI-Coder-4B-NVFP4** |
 |---|---|---|---|
+| **Generalization test** (121 unseen bugs, tests run to verify) | 10.1% | 82.9% | **38.0%*** |
 | **Live-60** (60 real-world engineering tasks, solved end-to-end in containers) | 15.0% | 21.7% | **15.0%** |
 | **Instruction-following** (IFEval) | 84.66 | 87.21 | **86.37** |
 | MMLU-Pro | 64.0% | 70.0% | **66.85%** |
 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.
 Our decontamination protocol is published with the model: none of these benchmark problems overlap the training data.
 ## What it does