codet5p-16b / config.json
yuewang-sf's picture
Update config.json
67962dd
{
"_name_or_path": "codet5p-16b",
"architectures": [
"CodeT5pEncoderDecoderModel"
],
"auto_map": {
"AutoConfig": "configuration_codet5p.CodeT5pConfig",
"AutoModel": "modeling_codet5p.CodeGenModel",
"AutoModelForSeq2SeqLM": "modeling_codet5p.CodeT5pEncoderDecoderModel"
},
"decoder": {
"_name_or_path": "codet5p-16b-decoder",
"activation_function": "gelu_new",
"add_cross_attention": true,
"architectures": [
"CodeT5pForCausalLM"
],
"attn_pdrop": 0.0,
"bad_words_ids": null,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"embd_pdrop": 0.0,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 50256,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_epsilon": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "codet5p_module",
"n_ctx": 2048,
"n_embd": 6144,
"n_head": 24,
"n_inner": null,
"n_layer": 34,
"n_positions": 2048,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"resid_pdrop": 0.0,
"return_dict": true,
"return_dict_in_generate": false,
"rotary_dim": 64,
"scale_attn_weights": true,
"sep_token_id": null,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": "GPT2Tokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float16",
"torchscript": false,
"transformers_version": "4.21.3",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 51200
},
"encoder": {
"_name_or_path": "codet5p-350m-encoder",
"activation_function": "gelu_new",
"add_cross_attention": false,
"architectures": [
"CodeT5pModel"
],
"attn_pdrop": 0.0,
"bad_words_ids": null,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"embd_pdrop": 0.0,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 50256,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_epsilon": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "codet5p_module",
"n_ctx": 2048,
"n_embd": 1024,
"n_head": 16,
"n_inner": null,
"n_layer": 20,
"n_positions": 2048,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"resid_pdrop": 0.0,
"return_dict": true,
"return_dict_in_generate": false,
"rotary_dim": 32,
"scale_attn_weights": true,
"sep_token_id": null,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": "GPT2Tokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float16",
"torchscript": false,
"transformers_version": "4.21.3",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 51200
},
"is_encoder_decoder": true,
"model_type": "codet5p",
"torch_dtype": "float16",
"transformers_version": null
}