ricemonster commited on
Commit
b3695af
·
verified ·
1 Parent(s): e320857

Upload folder using huggingface_hub

Browse files
._added_tokens.json ADDED
Binary file (4.1 kB). View file
 
._config.json ADDED
Binary file (4.1 kB). View file
 
._generation_config.json ADDED
Binary file (4.1 kB). View file
 
._merges.txt ADDED
Binary file (4.1 kB). View file
 
._model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._special_tokens_map.json ADDED
Binary file (4.1 kB). View file
 
._tokenizer.json ADDED
Binary file (4.1 kB). View file
 
._tokenizer_config.json ADDED
Binary file (4.1 kB). View file
 
._trainer_state.json ADDED
Binary file (4.1 kB). View file
 
._training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02783af53e23708725469e7f887d0422e5a74c296a6fb3f678a6608114bba812
3
+ size 4096
._vocab.json ADDED
Binary file (4.1 kB). View file
 
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<EOL>": 50000,
3
+ "<|UNKNOWN|>": 50001
4
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 2,
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.51.3",
33
+ "use_cache": true,
34
+ "vocab_size": 50002
35
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.51.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb6836f7adc40524930e7b607300a9a49a74f2b2b64ae68420cbf211207584f
3
+ size 496990848
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8000748728d9b006879a316403467c0bb168e80ce316eb0e5a753ca722e08c7
3
+ size 994075578
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23983290c1d8b8eaeeae80462dbefdfdbe8e1ed2d0722526f8e835988e036d7a
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4074c17470a32b647f021f4ac98a1ab1676b829a0f2a808d134a2df97c4e6a18
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa12e3e9e2e3ff5fd236bf40996d75489c996274a37f538af6674bd36e5dffbd
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "sep_token": "<EOL>",
18
+ "unk_token": {
19
+ "content": "<|UNKNOWN|>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<pad>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50000": {
30
+ "content": "<EOL>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50001": {
38
+ "content": "<|UNKNOWN|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "full_tokenizer_file": null,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
+ "sep_token": "<EOL>",
55
+ "tokenizer_class": "GPT2Tokenizer",
56
+ "unk_token": "<|UNKNOWN|>"
57
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2548ccee6d85db43dfb957544124cb6d5d710caa25c81f4da84a55f9f685d51
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff