Instructions to use Banaxi-Tech/muon-model-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Banaxi-Tech/muon-model-test with Transformers:

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

pipe = pipeline("text-generation", model="Banaxi-Tech/muon-model-test", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Banaxi-Tech/muon-model-test", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Banaxi-Tech/muon-model-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Banaxi-Tech/muon-model-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Banaxi-Tech/muon-model-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Banaxi-Tech/muon-model-test

SGLang

How to use Banaxi-Tech/muon-model-test 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 "Banaxi-Tech/muon-model-test" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Banaxi-Tech/muon-model-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Banaxi-Tech/muon-model-test" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Banaxi-Tech/muon-model-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Banaxi-Tech/muon-model-test with Docker Model Runner:
```
docker model run hf.co/Banaxi-Tech/muon-model-test
```

muon-model-test / training_metadata.json

Banaxi-Tech

Upload Muon FineWeb-Edu checkpoint at 24,999,591,936 tokens

225a21a verified 1 day ago

Raw

History Blame Contribute Delete

1.2 kB

	{
	"parameters": 9968128,
	"architecture": {
	"vocab_size": 8192,
	"hidden_size": 256,
	"num_hidden_layers": 10,
	"num_attention_heads": 4,
	"num_key_value_heads": 2,
	"head_dim": 64,
	"intermediate_size": 768,
	"max_position_embeddings": 4096,
	"rope_theta": 100000.0,
	"rms_norm_eps": 1e-06,
	"tie_word_embeddings": true
	},
	"dataset_id": "HuggingFaceFW/fineweb-edu",
	"dataset_config": "sample-100BT",
	"dataset_revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9",
	"tokenizer_repo": "BananaMind/BananaMind-2-Nano",
	"tokenizer_revision": "c8564d1bd3f6177221ed7e4f63ae5f281a677a1c",
	"optimizer": "Muon for hidden matrices; AdamW for embedding/norm",
	"muon_peak_lr": 0.05,
	"muon_momentum": 0.95,
	"muon_ns_steps": 5,
	"muon_adjust_lr_fn": "original",
	"adamw_peak_lr": 0.003,
	"global_batch": 132,
	"tokens_per_step": 540672,
	"steps": 46238,
	"tokens_seen": 24999591936,
	"target_tokens": 25000000000,
	"world_size": 8,
	"gpu_name": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
	"elapsed_seconds": 5169.452116250992,
	"average_tokens_per_second": 4836023.503808038,
	"estimated_training_flops": 4640871447860871168,
	"seed": 1337
	}