30 lines
744 B
JSON
30 lines
744 B
JSON
{
|
|
"architectures": [
|
|
"Gemma3ForCausalLM"
|
|
],
|
|
"model_type": "gemma3_text",
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.49.0",
|
|
"vocab_size": 262208,
|
|
"hidden_size": 2560,
|
|
"intermediate_size": 10240,
|
|
"num_hidden_layers": 34,
|
|
"num_attention_heads": 8,
|
|
"num_key_value_heads": 4,
|
|
"head_dim": 256,
|
|
"hidden_activation": "gelu_pytorch_tanh",
|
|
"max_position_embeddings": 8192,
|
|
"initializer_range": 0.02,
|
|
"rms_norm_eps": 1e-06,
|
|
"use_cache": true,
|
|
"pad_token_id": 0,
|
|
"eos_token_id": 1,
|
|
"bos_token_id": 2,
|
|
"tie_word_embeddings": true,
|
|
"rope_theta": 1000000,
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"query_pre_attn_scalar": 256,
|
|
"sliding_window": 1024,
|
|
"sliding_window_pattern": 6
|
|
} |