Instructions to use YuCollection/gemma-4-31B-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YuCollection/gemma-4-31B-bf16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="YuCollection/gemma-4-31B-bf16")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("YuCollection/gemma-4-31B-bf16")
model = AutoModelForImageTextToText.from_pretrained("YuCollection/gemma-4-31B-bf16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use YuCollection/gemma-4-31B-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YuCollection/gemma-4-31B-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YuCollection/gemma-4-31B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YuCollection/gemma-4-31B-bf16

SGLang

How to use YuCollection/gemma-4-31B-bf16 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 "YuCollection/gemma-4-31B-bf16" \
    --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": "YuCollection/gemma-4-31B-bf16",
		"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 "YuCollection/gemma-4-31B-bf16" \
        --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": "YuCollection/gemma-4-31B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YuCollection/gemma-4-31B-bf16 with Docker Model Runner:
```
docker model run hf.co/YuCollection/gemma-4-31B-bf16
```

gemma-4-31B-bf16 / config.json

YuCollection

Upload folder using huggingface_hub

a9b2a84 verified about 1 month ago

raw

history blame contribute delete

4.18 kB

	{
	"architectures": [
	"Gemma4ForConditionalGeneration"
	],
	"audio_config": null,
	"audio_token_id": 258881,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"dtype": "bfloat16",
	"eoa_token_id": 258883,
	"eoa_token_index": 258883,
	"eoi_token_id": 258882,
	"image_token_id": 258880,
	"initializer_range": 0.02,
	"model_type": "gemma4",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_k_eq_v": true,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"enable_moe_block": false,
	"eos_token_id": 1,
	"expert_intermediate_size": null,
	"final_logit_softcapping": 30.0,
	"global_head_dim": 512,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 5376,
	"hidden_size_per_layer_input": 0,
	"initializer_range": 0.02,
	"intermediate_size": 21504,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 262144,
	"model_type": "gemma4_text",
	"num_attention_heads": 32,
	"num_experts": null,
	"num_global_key_value_heads": 4,
	"num_hidden_layers": 60,
	"num_key_value_heads": 16,
	"num_kv_shared_layers": 0,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 1000000.0,
	"rope_type": "proportional"
	},
	"sliding_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"sliding_window": 1024,
	"tie_word_embeddings": true,
	"top_k_experts": null,
	"use_bidirectional_attention": "vision",
	"use_cache": true,
	"use_double_wide_mlp": false,
	"vocab_size": 262144,
	"vocab_size_per_layer_input": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.5.0.dev0",
	"video_token_id": 258884,
	"vision_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"default_output_length": 280,
	"dtype": "bfloat16",
	"global_head_dim": 72,
	"head_dim": 72,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"intermediate_size": 4304,
	"max_position_embeddings": 131072,
	"model_type": "gemma4_vision",
	"num_attention_heads": 16,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"patch_size": 16,
	"pooling_kernel_size": 3,
	"position_embedding_size": 10240,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 100.0,
	"rope_type": "default"
	},
	"standardize": true,
	"use_clipped_linears": false
	},
	"vision_soft_tokens_per_image": 280
	}