Instructions to use ApexDevelopment/tinygemma4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApexDevelopment/tinygemma4 with Transformers:

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

pipe = pipeline("text-generation", model="ApexDevelopment/tinygemma4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ApexDevelopment/tinygemma4")
model = AutoModelForCausalLM.from_pretrained("ApexDevelopment/tinygemma4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ApexDevelopment/tinygemma4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApexDevelopment/tinygemma4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApexDevelopment/tinygemma4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ApexDevelopment/tinygemma4

SGLang

How to use ApexDevelopment/tinygemma4 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 "ApexDevelopment/tinygemma4" \
    --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": "ApexDevelopment/tinygemma4",
		"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 "ApexDevelopment/tinygemma4" \
        --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": "ApexDevelopment/tinygemma4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ApexDevelopment/tinygemma4 with Docker Model Runner:
```
docker model run hf.co/ApexDevelopment/tinygemma4
```

tinygemma4 / training_state.json

ApexDevelopment

Publish corrected 4.96M-parameter Muon checkpoint

bad775e verified 6 days ago

Raw

History Blame Contribute Delete

1.25 kB

	{
	"step": 300000,
	"recipe": {
	"vocab_size": 8192,
	"num_hidden_layers": 12,
	"hidden_size": 128,
	"hidden_size_per_layer_input": 16,
	"intermediate_size": 384,
	"num_attention_heads": 4,
	"num_key_value_heads": 1,
	"head_dim": 32,
	"global_head_dim": 32,
	"sliding_window": 128,
	"max_position_embeddings": 2048,
	"full_attention_every": 4
	},
	"args": {
	"output_dir": "runs\\tiny-gemma4-v3-muon-corrected",
	"cache_dir": "runs\\tiny-gemma4-v3\\cache",
	"init_from": null,
	"data_dir": "data",
	"tokenizer_dir": "runs\\tiny-gemma4-v3\\tokenizer",
	"recipe": "v3",
	"data_mode": null,
	"max_steps": 300000,
	"batch_size": 32,
	"block_size": 256,
	"gradient_accumulation_steps": 1,
	"learning_rate": 0.00035,
	"min_learning_rate": 3.5e-05,
	"warmup_steps": 1000,
	"schedule_start_step": 0,
	"optimizer": "muon",
	"weight_decay": 0.1,
	"grad_clip": 1.0,
	"save_every": 10000,
	"eval_every": 1000,
	"eval_batches": 50,
	"train_char_limit": null,
	"valid_char_limit": null,
	"num_workers": 0,
	"seed": 1337,
	"resume": false,
	"compile": false
	},
	"time": "2026-07-22 21:53:23"
	}