Hugging Face's logo

anonymous-acl
/
models-moved

Model card Files
xet
Community
anonymous-acl commited on
Commit
8631aab
·
1 Parent(s): 6a94eca

corrected the tokenizers

Browse files
Files changed (18) hide show
  1. leolm-aeg/generation_config.json +1 -4
  2. leolm-aeg/special_tokens_map.json +21 -3
  3. leolm-aeg/tokenizer_config.json +23 -32
  4. leolm-p1-leo-errors-1M-p2-gec/generation_config.json +1 -4
  5. leolm-p1-leo-errors-1M-p2-gec/special_tokens_map.json +21 -3
  6. leolm-p1-leo-errors-1M-p2-gec/tokenizer_config.json +23 -32
  7. llama-2-ukr-aeg/generation_config.json +1 -4
  8. llama-2-ukr-aeg/special_tokens_map.json +21 -3
  9. llama-2-ukr-aeg/tokenizer_config.json +23 -32
  10. llama-2-ukr-p1-llama-errors-1M-p2-gec/generation_config.json +1 -4
  11. llama-2-ukr-p1-llama-errors-1M-p2-gec/special_tokens_map.json +21 -3
  12. llama-2-ukr-p1-llama-errors-1M-p2-gec/tokenizer_config.json +23 -32
  13. llammas-base-aeg/generation_config.json +1 -4
  14. llammas-base-aeg/special_tokens_map.json +21 -3
  15. llammas-base-aeg/tokenizer_config.json +23 -32
  16. llammas-base-p1-llammas-errors-1M-p2-gec/generation_config.json +1 -4
  17. llammas-base-p1-llammas-errors-1M-p2-gec/special_tokens_map.json +21 -3
  18. llammas-base-p1-llammas-errors-1M-p2-gec/tokenizer_config.json +23 -32
leolm-aeg/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
leolm-aeg/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
leolm-aeg/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
leolm-p1-leo-errors-1M-p2-gec/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
leolm-p1-leo-errors-1M-p2-gec/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
leolm-p1-leo-errors-1M-p2-gec/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
llama-2-ukr-aeg/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
llama-2-ukr-aeg/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
llama-2-ukr-aeg/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
llama-2-ukr-p1-llama-errors-1M-p2-gec/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
llama-2-ukr-p1-llama-errors-1M-p2-gec/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
llama-2-ukr-p1-llama-errors-1M-p2-gec/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
llammas-base-aeg/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
llammas-base-aeg/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
llammas-base-aeg/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
llammas-base-p1-llammas-errors-1M-p2-gec/generation_config.json CHANGED
@@ -2,11 +2,8 @@
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "return_dict": true,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.34.0.dev0",
11
- "use_cache": false
12
  }
 
2
  "bos_token_id": 1,
3
  "do_sample": true,
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.35.0"
 
9
  }
llammas-base-p1-llammas-errors-1M-p2-gec/special_tokens_map.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
llammas-base-p1-llammas-errors-1M-p2-gec/tokenizer_config.json CHANGED
@@ -1,44 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": false
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": null,
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": "/gpfs/space/home/taido/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852/tokenizer.json",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": true
 
 
 
 
 
44
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": false,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }