28 lines
639 B
JSON
28 lines
639 B
JSON
{
|
|
"architectures": [
|
|
"GemmaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 2,
|
|
"eos_token_id": 1,
|
|
"head_dim": 256,
|
|
"hidden_act": "gelu_pytorch_tanh",
|
|
"hidden_activation": null,
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 16384,
|
|
"max_position_embeddings": 8192,
|
|
"model_type": "gemma",
|
|
"num_attention_heads": 8,
|
|
"num_hidden_layers": 18,
|
|
"num_key_value_heads": 1,
|
|
"pad_token_id": 0,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_theta": 10000.0,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.39.3",
|
|
"use_cache": true,
|
|
"vocab_size": 256000
|
|
}
|