hamza-gpt2-xl / config.json
emrecanacikgoz's picture
Upload model
6bf4799 verified
raw
history blame
1.05 kB
{
"_name_or_path": "/kuacc/users/eacikgoz17/el-turco/turkish-factory/output-dir/gpt2-merged/gpt2-tr-leyla-5GB-1e-4-r32-a32-proj-bf16-merged",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 1600,
"n_head": 25,
"n_inner": null,
"n_layer": 48,
"n_positions": 1024,
"output_past": true,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float16",
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 50257
}