config.json

More experiments coming soon
{
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 24576,
"max_position_embeddings": 8192,
"model_type": "anime-ft",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 16,
"pad_token_id": 0,
"rms_norm_eps": 0.000001,
"rope_scaling": null,
"rope_theta": 10000,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.0.dev0",
"use_cache": true,
"vocab_size": 256000
}