CoolFace
Modelpublic

Free2035/AD_Problem_Router_v0

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes8downloads
config.json57 linesDownload Raw Back to root
1{2  "_sliding_window_pattern": 6,3  "architectures": [4    "Gemma3ForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "attn_logit_softcapping": null,9  "bos_token_id": 2,10  "eos_token_id": 106,11  "final_logit_softcapping": null,12  "head_dim": 256,13  "hidden_activation": "gelu_pytorch_tanh",14  "hidden_size": 640,15  "initializer_range": 0.02,16  "intermediate_size": 2048,17  "layer_types": [18    "sliding_attention",19    "sliding_attention",20    "sliding_attention",21    "sliding_attention",22    "sliding_attention",23    "full_attention",24    "sliding_attention",25    "sliding_attention",26    "sliding_attention",27    "sliding_attention",28    "sliding_attention",29    "full_attention",30    "sliding_attention",31    "sliding_attention",32    "sliding_attention",33    "sliding_attention",34    "sliding_attention",35    "full_attention"36  ],37  "max_position_embeddings": 32768,38  "model_type": "gemma3_text",39  "num_attention_heads": 4,40  "num_hidden_layers": 18,41  "num_key_value_heads": 1,42  "pad_token_id": 0,43  "query_pre_attn_scalar": 256,44  "rms_norm_eps": 1e-06,45  "rope_local_base_freq": 10000.0,46  "rope_scaling": null,47  "rope_theta": 1000000.0,48  "sliding_window": 512,49  "torch_dtype": "float16",50  "transformers_version": "4.55.2",51  "unsloth_fixed": true,52  "unsloth_version": "2025.8.9",53  "use_bidirectional_attention": false,54  "use_cache": true,55  "vocab_size": 26214456}57