SafeGem-27B / config.json
ywlee88's picture
Initial release of SafeGem-27B with Visual Guard Module
c0ae4dc verified
{
"architectures": [
"SafeGemForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_safegem.SafeGemConfig",
"AutoModel": "modeling_safegem.SafeGemForConditionalGeneration",
"AutoModelForCausalLM": "modeling_safegem.SafeGemForConditionalGeneration"
},
"boi_token_index": 255999,
"eoi_token_index": 256000,
"eos_token_id": [
1,
106
],
"image_token_index": 262144,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "safegem",
"num_safety_categories": 20,
"safety_categories": [
"safe",
"gender",
"race",
"religion",
"harassment",
"disability_discrimination",
"drug_crime",
"property_crime",
"facial_data",
"identity_data",
"physical_self_injury",
"suicide",
"animal_abuse",
"obscene_gestures",
"physical_altercation",
"terrorism",
"weapon_related_violence",
"sexual_content",
"financial_advice",
"medical_advice"
],
"safety_head_hidden_scale": 0.5,
"safety_loss_lambda": 1.0,
"safety_num_hidden_layers": 1,
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"cache_implementation": "hybrid",
"final_logit_softcapping": null,
"head_dim": 128,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 5376,
"initializer_range": 0.02,
"intermediate_size": 21504,
"max_position_embeddings": 131072,
"model_type": "gemma3_text",
"num_attention_heads": 32,
"num_hidden_layers": 62,
"num_key_value_heads": 16,
"query_pre_attn_scalar": 168,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": {
"factor": 8.0,
"rope_type": "linear"
},
"rope_theta": 1000000.0,
"sliding_window": 1024,
"sliding_window_pattern": 6,
"torch_dtype": "bfloat16",
"use_cache": true,
"vocab_size": 262208
},
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"vision_config": {
"attention_dropout": 0.0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 896,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 27,
"patch_size": 14,
"torch_dtype": "bfloat16",
"vision_use_head": false
}
}