Hugging Face's logo

charbelfeghalii
/
TLMs

Safetensors
Model card Files
xet
 Community
charbelfeghalii commited on
Commit
87470fa
·
verified ·
1 Parent(s): 6e7b3f6

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-10000/config.json +50 -0
  2. checkpoint-10000/generation_config.json +9 -0
  3. checkpoint-10000/model.safetensors +3 -0
  4. checkpoint-10000/tokenizer.json +0 -0
  5. checkpoint-10000/tokenizer_config.json +12 -0
  6. checkpoint-10000/training_state.pt +3 -0
  7. checkpoint-15000/config.json +50 -0
  8. checkpoint-15000/generation_config.json +9 -0
  9. checkpoint-15000/model.safetensors +3 -0
  10. checkpoint-15000/tokenizer.json +0 -0
  11. checkpoint-15000/tokenizer_config.json +12 -0
  12. checkpoint-15000/training_state.pt +3 -0
  13. checkpoint-20000/config.json +50 -0
  14. checkpoint-20000/generation_config.json +9 -0
  15. checkpoint-20000/model.safetensors +3 -0
  16. checkpoint-20000/tokenizer.json +0 -0
  17. checkpoint-20000/tokenizer_config.json +12 -0
  18. checkpoint-20000/training_state.pt +3 -0
  19. checkpoint-25000/config.json +50 -0
  20. checkpoint-25000/generation_config.json +9 -0
  21. checkpoint-25000/model.safetensors +3 -0
  22. checkpoint-25000/tokenizer.json +0 -0
  23. checkpoint-25000/tokenizer_config.json +12 -0
  24. checkpoint-25000/training_state.pt +3 -0
  25. checkpoint-30000/config.json +50 -0
  26. checkpoint-30000/generation_config.json +9 -0
  27. checkpoint-30000/model.safetensors +3 -0
  28. checkpoint-30000/tokenizer.json +0 -0
  29. checkpoint-30000/tokenizer_config.json +12 -0
  30. checkpoint-30000/training_state.pt +3 -0
  31. checkpoint-35000/config.json +50 -0
  32. checkpoint-35000/generation_config.json +9 -0
  33. checkpoint-35000/model.safetensors +3 -0
  34. checkpoint-35000/tokenizer.json +0 -0
  35. checkpoint-35000/tokenizer_config.json +12 -0
  36. checkpoint-35000/training_state.pt +3 -0
  37. checkpoint-40000/config.json +50 -0
  38. checkpoint-40000/generation_config.json +9 -0
  39. checkpoint-40000/model.safetensors +3 -0
  40. checkpoint-40000/tokenizer.json +0 -0
  41. checkpoint-40000/tokenizer_config.json +12 -0
  42. checkpoint-40000/training_state.pt +3 -0
  43. checkpoint-45000/config.json +50 -0
  44. checkpoint-45000/generation_config.json +9 -0
  45. checkpoint-45000/model.safetensors +3 -0
  46. checkpoint-45000/tokenizer.json +0 -0
  47. checkpoint-45000/tokenizer_config.json +12 -0
  48. checkpoint-45000/training_state.pt +3 -0
  49. checkpoint-5000/config.json +50 -0
  50. checkpoint-5000/generation_config.json +9 -0
checkpoint-10000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-10000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754d13cdac433601593ed51aaf7c95ce31b570104b13418458bdeb25ce9559fd
3
+ size 727652356
checkpoint-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-10000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4982b0511b1ec75c1c968577bd991eea2f952f957949f3eb31352e8fbc82af0
3
+ size 1455411352
checkpoint-15000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-15000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-15000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da0bbb53d945e2fb4ae2ede7823449db26f457399cae5c85d319a0991a9174a
3
+ size 727652356
checkpoint-15000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-15000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d82ae13a3ed86df2b67cab57e5b5e309ff9610ecd3ec452fc9c2328f9601a3
3
+ size 1455411352
checkpoint-20000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-20000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03dbeaa4e122e394938ab9384eda9233028aaa4cfb44e9d52fbf671b24cb557a
3
+ size 727652356
checkpoint-20000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-20000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6950572e0b82644398e5959f832ded483c6f3a7005c6db6c50796502f072167
3
+ size 1455411352
checkpoint-25000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-25000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-25000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15d34ea8adc93b2ca1abb45f3bb3b62a63600dbb2525539c9094e4232a2eaac
3
+ size 727652356
checkpoint-25000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-25000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b72c4eb1726f456efe42627c64516013b2d51f93e3413c9ff4e5aa1831df8b
3
+ size 1455411352
checkpoint-30000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-30000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033f8ebe7f2924210dadecf8c98bac96cafb9d5794cd781cc82f9e50a1be26ed
3
+ size 727652356
checkpoint-30000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-30000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744fb25df8c06dbe15712f263e994b502df04f36ddf015b2e576c82503ba023f
3
+ size 1455411352
checkpoint-35000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-35000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-35000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d8889ba4cdae4165005a72daa346bcb21d0e6ece7f7907d9219f1ed34ef98a
3
+ size 727652356
checkpoint-35000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-35000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-35000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94fb3a63b3b9bb16822a8aea94b1ce334679f1f4750ad9ec3378a61c42ea37b
3
+ size 1455411352
checkpoint-40000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-40000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1b0cd8352d6405e7885b3db761f3bfb65e20244f528b3abd9fc99d0c4c31ab
3
+ size 727652356
checkpoint-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-40000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-40000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4eab5c626f23f14ba3f2e7ad78dc0944e12764c3488b3c5f681dcbcb5afc9e
3
+ size 1455411352
checkpoint-45000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-45000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }
checkpoint-45000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744d40aee9f2e08d89ea9af823c9539ec04726e6b1dbae3817e725b31be5737a
3
+ size 727652356
checkpoint-45000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-45000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-45000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf180e91477ca2232997ed025b5bc3370105c7966582dc261ec42566db8e445
3
+ size 1455411352
checkpoint-5000/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLMTiered"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "dtype": "float32",
33
+ "embed_dropout": 0.0,
34
+ "eos_token_id": 50256,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "pad_token_id": null,
44
+ "resid_dropout": 0.0,
45
+ "tie_word_embeddings": true,
46
+ "transformers_version": "5.5.4",
47
+ "use_cache": false,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
checkpoint-5000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.5.4",
8
+ "use_cache": false
9
+ }