danielhanchen's picture
Upload Gemma3ForCausalLM
0d6bd5e verified
{
"_sliding_window_pattern": 6,
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"eos_token_id": 106,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 640,
"initializer_range": 0.02,
"intermediate_size": 2048,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"pad_token_id": 0,
"quantization_config": {
"include_input_output_embeddings": false,
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
}
},
"quant_type_kwargs": {},
"untie_embedding_weights": false
},
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 512,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.2",
"unsloth_fixed": true,
"use_bidirectional_attention": false,
"use_cache": true,
"vocab_size": 262144
}