Kirill Gelvan
add model
9f78596
raw
history blame
942 Bytes
{
"_name_or_path": "Grossmend/rudialogpt3_medium_based_on_gpt2",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 2048,
"n_embd": 1024,
"n_head": 16,
"n_inner": null,
"n_layer": 24,
"n_positions": 2048,
"n_special": 0,
"output_past": true,
"predict_special_tokens": true,
"resid_pdrop": 0.1,
"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,
"torch_dtype": "float32",
"transformers_version": "4.11.3",
"use_cache": true,
"vocab_size": 50257
}