CoolFace
Modelpublic

Lexsi/audit-harden-SafeGradTrainer-gemma3-4b-code

sourceHugging Faceupdated 4mo agoView on Hugging Face
0likes4downloads
config.json100 linesDownload Raw Back to root
1{2  "architectures": [3    "Gemma3ForConditionalGeneration"4  ],5  "boi_token_index": 255999,6  "dtype": "bfloat16",7  "eoi_token_index": 256000,8  "eos_token_id": [9    1,10    10611  ],12  "image_token_index": 262144,13  "initializer_range": 0.02,14  "mm_tokens_per_image": 256,15  "model_type": "gemma3",16  "text_config": {17    "_sliding_window_pattern": 6,18    "attention_bias": false,19    "attention_dropout": 0.0,20    "attn_logit_softcapping": null,21    "dtype": "bfloat16",22    "final_logit_softcapping": null,23    "head_dim": 256,24    "hidden_activation": "gelu_pytorch_tanh",25    "hidden_size": 2560,26    "initializer_range": 0.02,27    "intermediate_size": 10240,28    "layer_types": [29      "sliding_attention",30      "sliding_attention",31      "sliding_attention",32      "sliding_attention",33      "sliding_attention",34      "full_attention",35      "sliding_attention",36      "sliding_attention",37      "sliding_attention",38      "sliding_attention",39      "sliding_attention",40      "full_attention",41      "sliding_attention",42      "sliding_attention",43      "sliding_attention",44      "sliding_attention",45      "sliding_attention",46      "full_attention",47      "sliding_attention",48      "sliding_attention",49      "sliding_attention",50      "sliding_attention",51      "sliding_attention",52      "full_attention",53      "sliding_attention",54      "sliding_attention",55      "sliding_attention",56      "sliding_attention",57      "sliding_attention",58      "full_attention",59      "sliding_attention",60      "sliding_attention",61      "sliding_attention",62      "sliding_attention"63    ],64    "max_position_embeddings": 131072,65    "model_type": "gemma3_text",66    "num_attention_heads": 8,67    "num_hidden_layers": 34,68    "num_key_value_heads": 4,69    "query_pre_attn_scalar": 256,70    "rms_norm_eps": 1e-06,71    "rope_local_base_freq": 10000.0,72    "rope_scaling": {73      "factor": 8.0,74      "rope_type": "linear"75    },76    "rope_theta": 1000000.0,77    "sliding_window": 1024,78    "use_bidirectional_attention": false,79    "use_cache": true,80    "vocab_size": 26220881  },82  "transformers_version": "4.57.6",83  "use_cache": false,84  "vision_config": {85    "attention_dropout": 0.0,86    "dtype": "bfloat16",87    "hidden_act": "gelu_pytorch_tanh",88    "hidden_size": 1152,89    "image_size": 896,90    "intermediate_size": 4304,91    "layer_norm_eps": 1e-06,92    "model_type": "siglip_vision_model",93    "num_attention_heads": 16,94    "num_channels": 3,95    "num_hidden_layers": 27,96    "patch_size": 14,97    "vision_use_head": false98  }99}100