sho-takase commited on
Commit
ab033e8
1 Parent(s): 48f3ab9

Add model files

Browse files
Files changed (4) hide show
  1. config.json +1 -0
  2. pytorch_model.bin +3 -0
  3. spiece.model +3 -0
  4. tokenizer_config.json +15 -0
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 51200, "n_positions": 2048, "n_embd": 2304, "n_layer": 24, "n_head": 24, "n_inner": 9216, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 1, "eos_token_id": 2, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.28.1", "n_ctx": 2048, "gradient_checkpointing": false, "model_type": "gpt2"}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff64e459c67a9f02e7428704530f2ace343360047ad36bc036033c0e14a14ad
3
+ size 3505891417
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
3
+ size 1208648
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "extra_ids": 0,
3
+ "do_lower_case": false,
4
+ "keep_accents": true,
5
+ "bos_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>",
9
+ "mask_token": "<mask>",
10
+ "cls_token": "<cls>",
11
+ "sep_token": "<sep>",
12
+ "sp_model_kwargs": {},
13
+ "special_tokens_map_file": null,
14
+ "tokenizer_class": "T5Tokenizer"
15
+ }