Initial commit from mrm8488
Browse files- added_tokens.json +1 -0
- config.json +44 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|endoftext|>": 52000}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/GuaPeTe-2-tiny",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "gpt2",
|
22 |
+
"n_ctx": 1024,
|
23 |
+
"n_embd": 768,
|
24 |
+
"n_head": 12,
|
25 |
+
"n_inner": null,
|
26 |
+
"n_layer": 6,
|
27 |
+
"n_positions": 1024,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"task_specific_params": {
|
35 |
+
"text-generation": {
|
36 |
+
"do_sample": true,
|
37 |
+
"max_length": 50
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"transformers_version": "4.3.3",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 52001,
|
43 |
+
"xla_device": true
|
44 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15bef222a0566924c57a566c9893cc0f4ea79ca6853ef872df5b240c29971546
|
3 |
+
size 499075408
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "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, "max_len": 1024, "special_tokens_map_file": "/root/.cache/huggingface/transformers/cc4a7c4d36692dc96a2645ce7c3039a9d2976ffb22d8d42e10771d45cca07151.3ae9ae72462581d20e36bc528e9c47bb30cd671bb21add40ca0b24a0be9fac22", "name_or_path": "mrm8488/GuaPeTe-2-tiny", "errors": "replace"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0f6e652680c5ddbd12c11ac918ea9a3f3007f63a42b6f6a9b6a1467150b4ede
|
3 |
+
size 2159
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|