File size: 1,498 Bytes
a5a3835 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
{
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": [
1,
106
],
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 26,
"num_key_value_heads": 1,
"pad_token_id": 0,
"quantization_config": {
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"act_mapping_type": {
"_data": "SYMMETRIC",
"_type": "MappingType"
},
"layout": {
"_data": {},
"_type": "PlainLayout",
"_version": 1
},
"set_inductor_config": true,
"weight_only_decode": false
},
"_type": "Int8DynamicActivationInt8WeightConfig",
"_version": 1
}
},
"quant_type_kwargs": {}
},
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": 512,
"sliding_window_pattern": 6,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"vocab_size": 262144
}
|