gemma-3-1b-it-ONNX-GQA / config.json
Xenova's picture
Xenova HF staff
Upload folder using huggingface_hub
c0afc74 verified
{
"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,
"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": "4.51.0.dev0",
"use_cache": true,
"vocab_size": 262144,
"transformers.js_config": {
"kv_cache_dtype": {
"q4f16": "float16",
"fp16": "float16"
},
"use_external_data_format": {
"model.onnx": 1
}
}
}