Instructions to use 0xSero/Gemma-4-21B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/Gemma-4-21B with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/Gemma-4-21B")
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("0xSero/Gemma-4-21B")
model = AutoModelForMultimodalLM.from_pretrained("0xSero/Gemma-4-21B", 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 0xSero/Gemma-4-21B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/Gemma-4-21B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xSero/Gemma-4-21B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/Gemma-4-21B

SGLang

How to use 0xSero/Gemma-4-21B 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 "0xSero/Gemma-4-21B" \
    --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": "0xSero/Gemma-4-21B",
		"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 "0xSero/Gemma-4-21B" \
        --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": "0xSero/Gemma-4-21B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xSero/Gemma-4-21B with Docker Model Runner:
```
docker model run hf.co/0xSero/Gemma-4-21B
```

Gemma-4-21B / reap_args.yaml

0xSero

Add files using upload-large-folder tool

a2083b4 verified 5 months ago

Raw

History Blame Contribute Delete

2.11 kB

	cluster_args:
	cluster_description: null
	cluster_method: agglomerative
	compression_ratio: 0.2
	expert_sim: ttm
	frequency_penalty: true
	linkage_method: average
	max_cluster_size: null
	multi_layer: null
	num_clusters: null
	singleton_outlier_experts: false
	singleton_super_experts: false
	softmax_temperature: null
	ds_args:
	dataset_config_name: null
	dataset_name: theblackcat102/evol-codealpaca-v1:1000,open-r1/Mixture-of-Thoughts[code]:3480,open-r1/Mixture-of-Thoughts[math]:3578,open-r1/Mixture-of-Thoughts[science]:3576,Salesforce/xlam-function-calling-60k:1000,SWE-bench/SWE-smith-trajectories(tool):1000,qiaojin/PubMedQA[pqa_labeled]:800,derek-thomas/ScienceQA:800,openai/gsm8k[main]:4466,HuggingFaceH4/MATH-500(test):500,evalplus/humanevalplus(test):164,theblackcat102/evol-codealpaca-v1:1636
	dataset_test_split: test
	shuffle: true
	split: train
	eval_args:
	evalplus_tasks:
	- mbpp
	- humaneval
	greedy: true
	lm_eval_tasks:
	- winogrande
	- arc_challenge
	- arc_easy
	- boolq
	- hellaswag
	- mmlu
	- openbookqa
	- rte
	min_p: 0.0
	parallel_tasks: 32
	results_dir: null
	run_evalplus: true
	run_livecodebench: true
	run_lm_eval: true
	run_math: false
	run_wildbench: false
	server_log_file_name: server.log
	temperature: 0.7
	top_k: 20
	top_p: 0.8
	use_server: true
	vllm_port: 8000
	model_args:
	model_name: /mnt/llm_models/gemma-4-26B-A4B-it
	num_experts_per_tok_override: null
	obs_args:
	batch_size: 1
	distance_measure: angular
	model_max_length: 16384
	output_file_name: observations_22k_reap_gemma4.pt
	overwrite_observations: false
	record_pruning_metrics_only: true
	renormalize_router_weights: true
	return_vllm_tokens_prompt: false
	samples_per_category: 1024
	select_only_categories: null
	split_by_category: false
	truncate: false
	prune_args:
	n_experts_to_prune: null
	overwrite_pruned_model: false
	perserve_outliers: false
	perserve_super_experts: false
	prune_method: reap
	reap_args:
	debug: false
	do_eval: false
	plot_clusters: true
	profile: false
	run_observer_only: false
	seed: 42
	smoke_test: false