w11wo commited on
Commit
7a8fab6
1 Parent(s): cba9123

initial commit; fine-tuned on emotion twitter

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|endoftext|>": 50256}
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sundanese-gpt2-base-emotion-classifier",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_epsilon": 1e-05,
26
+ "model_type": "gpt2",
27
+ "n_ctx": 1024,
28
+ "n_embd": 768,
29
+ "n_head": 12,
30
+ "n_inner": null,
31
+ "n_layer": 12,
32
+ "n_positions": 1024,
33
+ "pad_token_id": 50256,
34
+ "resid_pdrop": 0.0,
35
+ "scale_attn_weights": true,
36
+ "summary_activation": null,
37
+ "summary_first_dropout": 0.1,
38
+ "summary_proj_to_labels": true,
39
+ "summary_type": "cls_index",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 50
45
+ }
46
+ },
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.8.2",
49
+ "use_cache": true,
50
+ "vocab_size": 50257
51
+ }
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:dac7058fc7724750065fe59387b263c059d60035cf2cdde4b24ef24289fbed48
3
+ size 510416295
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f591ba1ba6cf4237033a1ede4c295bbb24a0372e779a4a6692e13430dc08588e
3
+ size 497958928
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 128, "special_tokens_map_file": null, "name_or_path": "./pytorch-model", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff