Instructions to use exploitintel/cve-cwe-gemma4-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use exploitintel/cve-cwe-gemma4-12b with Transformers:

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

pipe = pipeline("text-generation", model="exploitintel/cve-cwe-gemma4-12b")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("exploitintel/cve-cwe-gemma4-12b")
model = AutoModelForImageTextToText.from_pretrained("exploitintel/cve-cwe-gemma4-12b")
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 exploitintel/cve-cwe-gemma4-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "exploitintel/cve-cwe-gemma4-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "exploitintel/cve-cwe-gemma4-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/exploitintel/cve-cwe-gemma4-12b

SGLang

How to use exploitintel/cve-cwe-gemma4-12b 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 "exploitintel/cve-cwe-gemma4-12b" \
    --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": "exploitintel/cve-cwe-gemma4-12b",
		"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 "exploitintel/cve-cwe-gemma4-12b" \
        --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": "exploitintel/cve-cwe-gemma4-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use exploitintel/cve-cwe-gemma4-12b with Docker Model Runner:
```
docker model run hf.co/exploitintel/cve-cwe-gemma4-12b
```

cve-cwe-gemma4-12b / config.json

exploitintel

Upload folder using huggingface_hub

83f96e7 verified 1 day ago

raw

history blame contribute delete

5.41 kB

	{
	"architectures": [
	"Gemma4UnifiedForConditionalGeneration"
	],
	"audio_config": {
	"_name_or_path": "",
	"architectures": null,
	"audio_embed_dim": 640,
	"chunk_size_feed_forward": 0,
	"torch_dtype": "bfloat16",
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"model_type": "gemma4_unified_audio",
	"output_attentions": false,
	"output_hidden_states": false,
	"problem_type": null,
	"return_dict": true,
	"rms_norm_eps": 1e-06
	},
	"audio_token_id": 258881,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"bos_token_id": 2,
	"torch_dtype": "bfloat16",
	"eoa_token_index": 258883,
	"eoi_token_id": 258882,
	"eos_token_id": 106,
	"image_token_id": 258880,
	"initializer_range": 0.02,
	"model_name": "unsloth/gemma-4-12b-it",
	"model_type": "gemma4_unified",
	"pad_token_id": 0,
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_k_eq_v": true,
	"bos_token_id": 2,
	"torch_dtype": "bfloat16",
	"enable_moe_block": false,
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"global_head_dim": 512,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 3840,
	"hidden_size_per_layer_input": 0,
	"initializer_range": 0.02,
	"intermediate_size": 15360,
	"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"
	],
	"max_position_embeddings": 262144,
	"model_type": "gemma4_unified_text",
	"moe_intermediate_size": null,
	"num_attention_heads": 16,
	"num_experts": null,
	"num_global_key_value_heads": 1,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"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,
	"unsloth_fixed": true,
	"unsloth_version": "2026.6.1",
	"use_cache": false,
	"video_token_id": 258884,
	"vision_config": {
	"_name_or_path": "",
	"architectures": null,
	"chunk_size_feed_forward": 0,
	"torch_dtype": "bfloat16",
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"mm_embed_dim": 3840,
	"mm_posemb_size": 1120,
	"model_type": "gemma4_unified_vision",
	"num_soft_tokens": 280,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_proj_dims": 3840,
	"patch_size": 16,
	"pooling_kernel_size": 3,
	"problem_type": null,
	"return_dict": true,
	"rms_norm_eps": 1e-06
	}
	}