gemfunc_2 / config.json
0x0daughter1's picture
Upload GemmaForCausalLM
45424ef verified
{
"_name_or_path": "/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_photography_dpo_cleaned_/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_transmitting_cleaned_/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_effectively_dpo_cleaned_/workspace/restore/finetuning-subnet-user/merge_test8/output_merge3_OwOpeepeepoopoo_gemmerica_gemma_effectively_m8m3_ep5_500/output_final_weights_OwOpeepeepoopoo_gemmerica_gemma_effectively_m8m3_ep5_500/output_final_weights_OwOpeepeepoopoo_gemmerica_bkp_gemma_lfg_1/output_final_weights",
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 204,
"eos_token_id": 213,
"head_dim": 256,
"hidden_act": "gelu",
"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_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.1",
"use_cache": false,
"vocab_size": 256000
}