igorls/gemma4-e4b-classifier
0274
1{2 "architectures": [3 "Gemma4ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "attention_k_eq_v": false,8 "bos_token_id": 2,9 "dtype": "bfloat16",10 "enable_moe_block": false,11 "eos_token_id": 1,12 "expert_intermediate_size": null,13 "final_logit_softcapping": 30.0,14 "global_head_dim": 512,15 "head_dim": 256,16 "hidden_activation": "gelu_pytorch_tanh",17 "hidden_size": 2560,18 "hidden_size_per_layer_input": 256,19 "initializer_range": 0.02,20 "intermediate_size": 10240,21 "layer_types": [22 "sliding_attention",23 "sliding_attention",24 "sliding_attention",25 "sliding_attention",26 "sliding_attention",27 "full_attention",28 "sliding_attention",29 "sliding_attention",30 "sliding_attention",31 "sliding_attention",32 "sliding_attention",33 "full_attention",34 "sliding_attention",35 "sliding_attention",36 "sliding_attention",37 "sliding_attention",38 "sliding_attention",39 "full_attention",40 "sliding_attention",41 "sliding_attention",42 "sliding_attention",43 "sliding_attention",44 "sliding_attention",45 "full_attention",46 "sliding_attention",47 "sliding_attention",48 "sliding_attention",49 "sliding_attention",50 "sliding_attention",51 "full_attention",52 "sliding_attention",53 "sliding_attention",54 "sliding_attention",55 "sliding_attention",56 "sliding_attention",57 "full_attention",58 "sliding_attention",59 "sliding_attention",60 "sliding_attention",61 "sliding_attention",62 "sliding_attention",63 "full_attention"64 ],65 "max_position_embeddings": 131072,66 "model_type": "gemma4_text",67 "moe_intermediate_size": null,68 "num_attention_heads": 8,69 "num_experts": null,70 "num_global_key_value_heads": null,71 "num_hidden_layers": 42,72 "num_key_value_heads": 2,73 "num_kv_shared_layers": 18,74 "pad_token_id": 0,75 "rms_norm_eps": 1e-06,76 "rope_parameters": {77 "full_attention": {78 "partial_rotary_factor": 0.25,79 "rope_theta": 1000000.0,80 "rope_type": "proportional"81 },82 "sliding_attention": {83 "rope_theta": 10000.0,84 "rope_type": "default"85 }86 },87 "sliding_window": 512,88 "tie_word_embeddings": true,89 "top_k_experts": null,90 "transformers_version": "5.8.0",91 "use_bidirectional_attention": null,92 "use_cache": true,93 "use_double_wide_mlp": false,94 "vocab_size": 262144,95 "vocab_size_per_layer_input": 26214496}97 