add files

This commit is contained in:
patil-suraj 2021-03-30 15:00:24 +00:00
parent d31f415805
commit ef4a5f2fa1
7 changed files with 50081 additions and 0 deletions

1
.gitattributes vendored
View File

@ -14,3 +14,4 @@
*.pb filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

73
config.json Normal file
View File

@ -0,0 +1,73 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPTNeoForCausalLM"
],
"attention_dropout": 0,
"attention_layers": [
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local",
"global",
"local"
],
"attention_types": [
[
[
"global",
"local"
],
16
]
],
"bos_token_id": 50256,
"embed_dropout": 0,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": null,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neo",
"num_heads": 20,
"num_layers": 32,
"resid_dropout": 0,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.5.0.dev0",
"use_cache": true,
"vocab_size": 50257,
"window_size": 256,
"tokenizer_class": "GPT2Tokenizer"
}

50001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

BIN
pytorch_model.bin (Stored with Git LFS) Normal file

Binary file not shown.

1
special_tokens_map.json Normal file
View File

@ -0,0 +1 @@
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

1
tokenizer_config.json Normal file
View File

@ -0,0 +1 @@
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long