Commit
•
f9964c3
1
Parent(s):
ec4a023
Version 1 initial push
Browse files- Version 1/added_tokens.json +1 -0
- Version 1/config.json +30 -0
- Version 1/merges.txt +0 -0
- Version 1/special_tokens_map.json +1 -0
- Version 1/tf_model.h5 +3 -0
- Version 1/tokenizer_config.json +1 -0
- Version 1/vocab.json +0 -0
Version 1/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|endoftext|>": 50000}
|
Version 1/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"transformers_version": "4.16.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50000
|
30 |
+
}
|
Version 1/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Version 1/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
|
Version 1/tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:900719e63861a98eff933af082e18486d91c36b5739b0fb09f4fc87170218cad
|
3 |
+
size 497145960
|
Version 1/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "tokenized_data", "tokenizer_class": "GPT2Tokenizer"}
|
Version 1/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|