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 / README.md

Banaxi-Tech

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

225a21a verified 1 day ago

preview code

Raw

History Blame Contribute Delete

2.55 kB

metadata

license: apache-2.0
language:
  - en
library_name: transformers
pipeline_tag: text-generation
datasets:
  - HuggingFaceFW/fineweb-edu
tags:
  - causal-lm
  - base-model
  - bananamind2-nano
  - muon
  - fineweb-edu
  - optimizer-comparison
  - custom-code
  - trust-remote-code

BananaMind 2 Nano Muon FineWeb-Edu Test

This experimental base model uses the exact BananaMind 2 Nano architecture and tokenizer. It was trained from scratch with stock PyTorch Muon on the hidden matrices and AdamW on the tied embedding and normalization weights, using only streamed FineWeb-Edu data for 24,999,591,936 custom-tokenizer tokens.

Architecture

Field	Value
Parameters	9,968,128
Layers	10
Hidden size	256
Intermediate size	768
Query heads	4
KV heads	2
Head dimension	64
Context	4,096
Vocabulary	8,192
Embeddings	Tied
Attention	GQA, pre-RoPE QK norm
MLP	SwiGLU
Position encoding	RoPE, theta 100,000

Training

Field	Value
Dataset	`HuggingFaceFW/fineweb-edu` / `sample-100BT`
Dataset revision	`87f09149ef4734204d70ed1d046ddc9ca3f2b8f9`
Data access	Streaming
Hidden-matrix optimizer	PyTorch Muon (`adjust_lr_fn="original"`)
Muon peak learning rate	0.05
Muon momentum	0.95, Nesterov
Muon Newton-Schulz steps	5
Embedding/norm optimizer	AdamW
AdamW peak learning rate	0.003
AdamW betas	(0.9, 0.95)
Global batch	132 sequences
Tokens per optimizer step	540,672
Optimizer steps	46,238
Warmup	1,750 steps
Schedule	Warmup-stable-decay, final 15% cosine cooldown
Weight decay	0.1, then 0.01 after 12,000,000,000 tokens
Precision	bfloat16 autocast, float32 master weights
Hardware	8 x NVIDIA RTX PRO 6000 Blackwell Server Edition
Seed	1337

The original Nano effective batch was 12 micro-batches x 11 accumulation steps = 132 sequences. This distributed run preserves that exact global batch. Ranks receive 16 or 17 sequences and scale their local mean losses so DDP's averaged gradient is the true 132-sequence global mean.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Banaxi-Tech/muon-model-test"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map="auto",
)

This is a base model, not an instruction-tuned chat model.