Hugging Face's logo

ayousanz
/
mistral-0.3b-backup

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
ayousanz commited on
Commit
c29b08e
·
verified ·
1 Parent(s): 0661eed

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. checkpoint-38000/config.json +25 -0
  2. checkpoint-38000/generation_config.json +6 -0
  3. checkpoint-38000/model.safetensors +3 -0
  4. checkpoint-38000/optimizer.pt +3 -0
  5. checkpoint-38000/rng_state_0.pth +3 -0
  6. checkpoint-38000/rng_state_1.pth +3 -0
  7. checkpoint-38000/scheduler.pt +3 -0
  8. checkpoint-38000/special_tokens_map.json +30 -0
  9. checkpoint-38000/spiece.model +3 -0
  10. checkpoint-38000/tokenizer.json +0 -0
  11. checkpoint-38000/tokenizer_config.json +47 -0
  12. checkpoint-38000/trainer_state.json +0 -0
  13. checkpoint-38000/training_args.bin +3 -0
  14. checkpoint-39000/config.json +25 -0
  15. checkpoint-39000/generation_config.json +6 -0
  16. checkpoint-39000/model.safetensors +3 -0
  17. checkpoint-39000/optimizer.pt +3 -0
  18. checkpoint-39000/rng_state_0.pth +3 -0
  19. checkpoint-39000/rng_state_1.pth +3 -0
  20. checkpoint-39000/scheduler.pt +3 -0
  21. checkpoint-39000/special_tokens_map.json +30 -0
  22. checkpoint-39000/spiece.model +3 -0
  23. checkpoint-39000/tokenizer.json +0 -0
  24. checkpoint-39000/tokenizer_config.json +47 -0
  25. checkpoint-39000/trainer_state.json +0 -0
  26. checkpoint-39000/training_args.bin +3 -0
  27. checkpoint-40000/config.json +25 -0
  28. checkpoint-40000/generation_config.json +6 -0
  29. checkpoint-40000/model.safetensors +3 -0
  30. checkpoint-40000/optimizer.pt +3 -0
  31. checkpoint-40000/rng_state_0.pth +3 -0
  32. checkpoint-40000/rng_state_1.pth +3 -0
  33. checkpoint-40000/scheduler.pt +3 -0
  34. checkpoint-40000/special_tokens_map.json +30 -0
  35. checkpoint-40000/spiece.model +3 -0
  36. checkpoint-40000/tokenizer.json +0 -0
  37. checkpoint-40000/tokenizer_config.json +47 -0
  38. checkpoint-40000/trainer_state.json +0 -0
  39. checkpoint-40000/training_args.bin +3 -0
checkpoint-38000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2400,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 1024,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 50257
25
+ }
checkpoint-38000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }
checkpoint-38000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51546f0bd57b76e9a61c74d85ddbe6cab231ea035bb94d52b5d692eb9d391053
3
+ size 1421709600
checkpoint-38000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7b01159bf7c39b34ee0192dea43c2f1423e466f1611cc748aa09ceaf69b99d
3
+ size 712761658
checkpoint-38000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa8add8a1bc641aaa9978d9ad625a6457a7eb2e3fa28092586292827299daff
3
+ size 14512
checkpoint-38000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2ed9d69e1a6364a05a3da807e602295cfb8a4469e841c042c029705b99da42
3
+ size 14512
checkpoint-38000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2276cd7d97281c4f9beb1abcd305754011d63d1c5c37639d14f301ac7fc144f4
3
+ size 1064
checkpoint-38000/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-38000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
3
+ size 1249735
checkpoint-38000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-38000/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "</s>",
40
+ "extra_ids": 0,
41
+ "legacy": true,
42
+ "model_max_length": 50000,
43
+ "pad_token": "[PAD]",
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "T5Tokenizer",
46
+ "unk_token": "[UNK]"
47
+ }
checkpoint-38000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-38000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e155e14ea10bc818c6d546606d5c422939b7900b506b462ed99a246bcc2dbf79
3
+ size 4600
checkpoint-39000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2400,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 1024,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 50257
25
+ }
checkpoint-39000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }
checkpoint-39000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4fbec2d5054748c4162187bbc7d8fea186c5e8c3a8bc1b0d844b1ca871d317
3
+ size 1421709600
checkpoint-39000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1221195cfb6e1ce7bc6b71d2981a924c6ba4fea53fb778cffdcc5f22117068ee
3
+ size 712761658
checkpoint-39000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf69441d6980c53352a500cc7317cc2141f8566929fac4c41971ab27dc71d8a1
3
+ size 14512
checkpoint-39000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42877fe80c422e7f7e840cb1b5d9e586eadfa8e48788c8dc471481a547b3fa1
3
+ size 14512
checkpoint-39000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ff85a2cf7a600b833dee88a84d43f455a73315c6fcaa1871f9fd65bbaba45f
3
+ size 1064
checkpoint-39000/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-39000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
3
+ size 1249735
checkpoint-39000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-39000/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "</s>",
40
+ "extra_ids": 0,
41
+ "legacy": true,
42
+ "model_max_length": 50000,
43
+ "pad_token": "[PAD]",
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "T5Tokenizer",
46
+ "unk_token": "[UNK]"
47
+ }
checkpoint-39000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-39000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e155e14ea10bc818c6d546606d5c422939b7900b506b462ed99a246bcc2dbf79
3
+ size 4600
checkpoint-40000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2400,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 1024,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 50257
25
+ }
checkpoint-40000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }
checkpoint-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389eb75c733243e74d68ecddd70c9977af748e811b7dae1820aa0dfa3e12d20b
3
+ size 1421709600
checkpoint-40000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1104d13b990808b5fc3d3e5fdfeea912de6e558dce87be56e399dde7ab6df0aa
3
+ size 712761658
checkpoint-40000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe798d92905762b3e0c0c393c7fbf29299588d067d6bc081fa009fa72dfa242e
3
+ size 14512
checkpoint-40000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07ba16fc7c47b52412aedde9129efaf5417c7dbfafc9d279b3d6c9d97743601
3
+ size 14512
checkpoint-40000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71ca4141b873f542743fb0bcea99b12b9fe9be7215e396543e7e3c1e33670be
3
+ size 1064
checkpoint-40000/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-40000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
3
+ size 1249735
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "</s>",
40
+ "extra_ids": 0,
41
+ "legacy": true,
42
+ "model_max_length": 50000,
43
+ "pad_token": "[PAD]",
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "T5Tokenizer",
46
+ "unk_token": "[UNK]"
47
+ }
checkpoint-40000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-40000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e155e14ea10bc818c6d546606d5c422939b7900b506b462ed99a246bcc2dbf79
3
+ size 4600