Instructions to use biosai-hf/Inkling-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use biosai-hf/Inkling-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="biosai-hf/Inkling-MXFP4")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("biosai-hf/Inkling-MXFP4")
model = AutoModelForMultimodalLM.from_pretrained("biosai-hf/Inkling-MXFP4", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use biosai-hf/Inkling-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "biosai-hf/Inkling-MXFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "biosai-hf/Inkling-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/biosai-hf/Inkling-MXFP4

SGLang

How to use biosai-hf/Inkling-MXFP4 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 "biosai-hf/Inkling-MXFP4" \
    --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": "biosai-hf/Inkling-MXFP4",
		"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 "biosai-hf/Inkling-MXFP4" \
        --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": "biosai-hf/Inkling-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use biosai-hf/Inkling-MXFP4 with Docker Model Runner:
```
docker model run hf.co/biosai-hf/Inkling-MXFP4
```

biosai-official commited on Aug 3

Commit

6d124e5

verified ·

1 Parent(s): 3b1eb2c

Upload .gitattributes with huggingface_hub

Browse files

Files changed (1) hide show

.gitattributes +114 -35

.gitattributes CHANGED Viewed

@@ -1,35 +1,114 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

+model-00050-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00014-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00082-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00044-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00052-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00047-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00070-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00099-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00040-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00029-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00043-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00019-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00012-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00084-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00101-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00093-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00090-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00054-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00035-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00030-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00071-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00021-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00018-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00026-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00034-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00069-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00059-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00013-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00104-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00038-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+mtp.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00049-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00028-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00027-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00015-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00105-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00048-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00087-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00085-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00017-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00046-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00020-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00051-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00079-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00057-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00036-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00081-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00100-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00097-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00080-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00032-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00061-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00074-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00060-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00066-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00102-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00095-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00041-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00078-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00083-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00058-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00045-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00067-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00072-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00103-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00024-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00031-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00096-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00023-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00092-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00076-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00063-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00107-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00098-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00089-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00106-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00075-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00025-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00077-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00108-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00086-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00065-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00039-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00062-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00094-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00068-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00091-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00022-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00088-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00016-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00073-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00033-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00064-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00056-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00037-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00053-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00042-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00055-of-00108.safetensors filter=lfs diff=lfs merge=lfs -text
+tiktoken/tokenizer.model filter=lfs diff=lfs merge=lfs -text
+lora/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
+lora/compare_sample_train_data.pt filter=lfs diff=lfs merge=lfs -text
+adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text