CCGwGPT2extep3reduce / config.json
{
"_name_or_path": "jamiewjm/CCGwGPT2",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"do_sample": true,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"max_length": 100,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"no_repeat_ngram_size": 3,
"num_return_sequences": 5,
"output_past": true,
"reorder_and_upcast_attn": false,
"repetition_penalty": 1.3,
"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,
"eos_token_id": 0,
"max_length": 100,
"no_repeat_ngram_size": 3,
"num_return_sequences": 5,
"pad_token_id": 0,
"repetition_penalty": 1.3,
"temperature": 0.7,
"top_k": 8,
"top_p": 0.7
}
},
"tokenizer_class": "BertTokenizerFast",
"top_k": 5,
"top_p": 0.7,
"torch_dtype": "float32",
"transformers_version": "4.12.3",
"use_cache": true,
"vocab_size": 25811
}