Hugging Face's logo

TheRootOf3
/
low-resource-language-model-adaptation

Model card Files
xet
Community
TheRootOf3 commited on
Commit
5178a42
·
verified ·
1 Parent(s): 292261a

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/all_results.json +1 -0
  2. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/config.json +31 -0
  3. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/generation_config.json +7 -0
  4. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/merges.txt +0 -0
  5. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/pytorch_model.bin +3 -0
  6. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/special_tokens_map.json +30 -0
  7. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/tokenizer.json +0 -0
  8. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/tokenizer_config.json +30 -0
  9. adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/vocab.json +0 -0
  10. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/all_results.json +1 -0
  11. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/config.json +31 -0
  12. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/generation_config.json +7 -0
  13. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/merges.txt +0 -0
  14. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/pytorch_model.bin +3 -0
  15. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/special_tokens_map.json +30 -0
  16. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/tokenizer.json +0 -0
  17. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/tokenizer_config.json +30 -0
  18. adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/vocab.json +0 -0
  19. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/all_results.json +1 -0
  20. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/config.json +31 -0
  21. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/generation_config.json +7 -0
  22. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/merges.txt +0 -0
  23. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/pytorch_model.bin +3 -0
  24. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/special_tokens_map.json +30 -0
  25. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/tokenizer.json +0 -0
  26. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/tokenizer_config.json +30 -0
  27. adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/vocab.json +0 -0
  28. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/all_results.json +1 -0
  29. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/config.json +31 -0
  30. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/generation_config.json +7 -0
  31. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/merges.txt +0 -0
  32. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/pytorch_model.bin +3 -0
  33. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/special_tokens_map.json +30 -0
  34. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/tokenizer.json +0 -0
  35. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/tokenizer_config.json +30 -0
  36. adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/vocab.json +0 -0
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 2.545044190718372}
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 8192,
16
+ "hidden_size": 2048,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2048
31
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.39.3"
7
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29f034eac8312ebc3aab19d954ec953e7a5e773ac76cb3ab0b1a734bb16e00b
3
+ size 2837562526
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-amh/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 6.294572941246555}
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 8192,
16
+ "hidden_size": 2048,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2048
31
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.39.3"
7
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6487130799970bd57ffc558c99a587ef1711d9bef6ca3ef0c60cd12d0ad418
3
+ size 2837562526
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-hau/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 4.721898985957784}
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 8192,
16
+ "hidden_size": 2048,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2048
31
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.39.3"
7
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b720fd8f998d1e3d80612be7dffd72dd3c5c65e68cd78bcfe36bb7e47b486b11
3
+ size 2837562526
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-ibo/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 5.156806843919794}
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 8192,
16
+ "hidden_size": 2048,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2048
31
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.39.3"
7
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635099f752440993e234fa872d67d61e73aa80328b11a988f8ed80412dba81e7
3
+ size 2837562526
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
adapted_models/cpt/prop-0/tokenizer-opt/100M-yor/vocab.json ADDED
The diff for this file is too large to render. See raw diff