Instructions to use malvavisc0/OxCoder-9B-gptq-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use malvavisc0/OxCoder-9B-gptq-int4 with Transformers:

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

pipe = pipeline("text-generation", model="malvavisc0/OxCoder-9B-gptq-int4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("malvavisc0/OxCoder-9B-gptq-int4")
model = AutoModelForMultimodalLM.from_pretrained("malvavisc0/OxCoder-9B-gptq-int4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use malvavisc0/OxCoder-9B-gptq-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "malvavisc0/OxCoder-9B-gptq-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malvavisc0/OxCoder-9B-gptq-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/malvavisc0/OxCoder-9B-gptq-int4

SGLang

How to use malvavisc0/OxCoder-9B-gptq-int4 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 "malvavisc0/OxCoder-9B-gptq-int4" \
    --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": "malvavisc0/OxCoder-9B-gptq-int4",
		"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 "malvavisc0/OxCoder-9B-gptq-int4" \
        --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": "malvavisc0/OxCoder-9B-gptq-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use malvavisc0/OxCoder-9B-gptq-int4 with Docker Model Runner:
```
docker model run hf.co/malvavisc0/OxCoder-9B-gptq-int4
```

malvavisc0 commited on Sep 14

Commit

552fb23

verified ·

1 Parent(s): 7cd67ac

Card: name quantize toolchain and verification host

Browse files

Files changed (1) hide show

README.md +11 -2

README.md CHANGED Viewed

@@ -84,5 +84,14 @@ Notes:
 | Provenance | `aft_provenance.json` (pinned source revision, seeds, config) |
 | Per-layer log | `quant_log.csv` |
-— quantized with [aft](https://github.com/malvavisc0/aft), the Aria
-Finetuner pipeline.

 | Provenance | `aft_provenance.json` (pinned source revision, seeds, config) |
 | Per-layer log | `quant_log.csv` |
+**Toolchain:** quantized with [aft](https://github.com/malvavisc0/aft)
+(the Aria Finetuner pipeline) driving gptqmodel 7.3.4 / torch
+2.13.0+cu130 / transformers 5.15.0 on an NVIDIA GB10 (DGX Spark,
+aarch64, 128 GB unified). Quant error: mean 2.3e-5, worst 1.1e-4
+(200 text modules).
+**Verified on consumer hardware:** RTX A5000 16 GB (sm_86, plain CUDA —
+no GB10 dependency) with vLLM 0.28.0: 5/5 behavioral probes (math with
+closed think blocks, exec-verified Kadane's incl. the all-negative
+case, parsed XML tool call), 45 tok/s decode on a short coding probe,
+40 tok/s at 31k context, 0.06 s TTFT.