Instructions to use brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction with Transformers:

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

pipe = pipeline("text-generation", model="brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction")
model = AutoModelForCausalLM.from_pretrained("brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction", 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 brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction

SGLang

How to use brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction 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 "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction" \
    --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": "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction",
		"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 "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction" \
        --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": "brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction with Docker Model Runner:
```
docker model run hf.co/brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction
```

Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction / SHA256SUMS

brandonmusic

Publish sealed causal ShapleyMCG validation reconstruction

c3447f3 verified about 1 month ago

Raw History Blame Contribute Delete

2.66 kB

	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 .gitattributes
	832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e LICENSE
	8b0d698912d1f8135358e14802292e2b5940c82ecc12d01d1aa5d2561f138ba4 README.md
	5916655c0461089811ff73908151ce5f927b58bf93a279bce85ed3988fcd0eb7 assembly-plan.json
	7e4142150e976c6b4796adf88fce0a2a23e581ed63bcede7e1d69a645e73b362 config.json
	8c970692323e3ea0e9b8b0a4dca79388d31226e41f83c9fd6014804280ebf6e8 generation_config.json
	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 merges.txt
	c9b5c7334a9121b320ad65b9287093e2fd9907290f7ea6fdfefcfa874f055004 model-00001-of-00016.safetensors
	2f6de21e609c26a712207ceab4b425e8a1538bb7da5990a0a907d1458cb17280 model-00002-of-00016.safetensors
	f71fab544d25a1592216d4478317f68c1830afa60718a2057fb14a7636e56122 model-00003-of-00016.safetensors
	8a2cc211262f4427ccfe4600bd8e7d5ec1d833dca331931f57053726f5fdf5f0 model-00004-of-00016.safetensors
	7eb80306a85c8e68c84b76154c5a8f58fc02d7c79d41027f6687987c94614f90 model-00005-of-00016.safetensors
	1bea2d38250d71352cb74be9a64e3419426cd097230928783829b467f649ed36 model-00006-of-00016.safetensors
	b48bb28aa61c119b28b705e16c494b80f2e5b1ff6c588d8c19c08b1673e55af3 model-00007-of-00016.safetensors
	37a016c5c3966de26b7226456bf5279fb68613dbb2bec233e29b8c4c23df6a66 model-00008-of-00016.safetensors
	404546eeb2a6140cc98b29dafd9cd5c898f70583b790ed64cfab1f51d77999b5 model-00009-of-00016.safetensors
	eba7a5ecf9c7129c608ad5b0efaa016311792263a66baadbd7aee960ed4a430a model-00010-of-00016.safetensors
	77b8101cba36df0950b36bb7cfa2b36e5d8ea6b3d880e91cd5c7ca2a736e388f model-00011-of-00016.safetensors
	66884ad8bb17e5290cfd80b7dc1682fd2b2628337609742e821aaac3b97e550c model-00012-of-00016.safetensors
	6d594ce5d49a5679827590b8f37d6a47aa6210449f7fabf051f070307b578f40 model-00013-of-00016.safetensors
	0d5686d1c3454ad5b05a286a90784edc6cc7a218d37f9cf4beee4702901ac6f6 model-00014-of-00016.safetensors
	f9ab1d45001a829c49d3d2027a9743eb02992b808a86d22899a0f0942e9860ae model-00015-of-00016.safetensors
	32f72260adb875a0e7e5c4c5791d55f97028c79bde971f28ef0dd5a5d625ee34 model-00016-of-00016.safetensors
	e7bcbbd124c5d088ca5414837d6945ec87bce6c0d5989c119fd676edc145eaa6 model-logit-verification.json
	df0d481ec595c55a0ba58426d517390c6214a566ec4ff1c8fc4bbce9f57b3c24 model.safetensors.index.json
	99948f33ab75abbba54da75b515665f45e75cf25e7dadc2ee5387222a840322d provenance.json
	c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539 tokenizer.json
	3c04ed3ca964ea2f6b2b5faf0dc4d31aec1cb1e8b4bcf63f402d295046b422b5 tokenizer_config.json
	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 vocab.json