Hugging Face's logo

jekunz
/
Gemma-3-1B-pt-sv-CPT

Safetensors
gemma3_text
Model card Files
xet
 Community
jekunz commited on
Commit
38ac099
·
verified ·
1 Parent(s): fdd10d5

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. .gitattributes +4 -0
  2. checkpoint-60000/config.json +64 -0
  3. checkpoint-60000/generation_config.json +13 -0
  4. checkpoint-60000/model.safetensors +3 -0
  5. checkpoint-60000/optimizer.pt +3 -0
  6. checkpoint-60000/rng_state_0.pth +3 -0
  7. checkpoint-60000/rng_state_1.pth +3 -0
  8. checkpoint-60000/rng_state_2.pth +3 -0
  9. checkpoint-60000/rng_state_3.pth +3 -0
  10. checkpoint-60000/rng_state_4.pth +3 -0
  11. checkpoint-60000/rng_state_5.pth +3 -0
  12. checkpoint-60000/rng_state_6.pth +3 -0
  13. checkpoint-60000/rng_state_7.pth +3 -0
  14. checkpoint-60000/scheduler.pt +3 -0
  15. checkpoint-60000/special_tokens_map.json +33 -0
  16. checkpoint-60000/tokenizer.json +3 -0
  17. checkpoint-60000/tokenizer_config.json +0 -0
  18. checkpoint-60000/trainer_state.json +0 -0
  19. checkpoint-60000/training_args.bin +3 -0
  20. checkpoint-70000/config.json +64 -0
  21. checkpoint-70000/generation_config.json +13 -0
  22. checkpoint-70000/model.safetensors +3 -0
  23. checkpoint-70000/optimizer.pt +3 -0
  24. checkpoint-70000/rng_state_0.pth +3 -0
  25. checkpoint-70000/rng_state_1.pth +3 -0
  26. checkpoint-70000/rng_state_2.pth +3 -0
  27. checkpoint-70000/rng_state_3.pth +3 -0
  28. checkpoint-70000/rng_state_4.pth +3 -0
  29. checkpoint-70000/rng_state_5.pth +3 -0
  30. checkpoint-70000/rng_state_6.pth +3 -0
  31. checkpoint-70000/rng_state_7.pth +3 -0
  32. checkpoint-70000/scheduler.pt +3 -0
  33. checkpoint-70000/special_tokens_map.json +33 -0
  34. checkpoint-70000/tokenizer.json +3 -0
  35. checkpoint-70000/tokenizer_config.json +0 -0
  36. checkpoint-70000/trainer_state.json +0 -0
  37. checkpoint-70000/training_args.bin +3 -0
  38. checkpoint-78125/config.json +64 -0
  39. checkpoint-78125/generation_config.json +13 -0
  40. checkpoint-78125/model.safetensors +3 -0
  41. checkpoint-78125/optimizer.pt +3 -0
  42. checkpoint-78125/rng_state_0.pth +3 -0
  43. checkpoint-78125/rng_state_1.pth +3 -0
  44. checkpoint-78125/rng_state_2.pth +3 -0
  45. checkpoint-78125/rng_state_3.pth +3 -0
  46. checkpoint-78125/rng_state_4.pth +3 -0
  47. checkpoint-78125/rng_state_5.pth +3 -0
  48. checkpoint-78125/rng_state_6.pth +3 -0
  49. checkpoint-78125/rng_state_7.pth +3 -0
  50. checkpoint-78125/scheduler.pt +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-60000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-70000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-78125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-60000/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_local_base_freq": 10000,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000,
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 6,
60
+ "transformers_version": "4.57.3",
61
+ "use_bidirectional_attention": false,
62
+ "use_cache": true,
63
+ "vocab_size": 262144
64
+ }
checkpoint-60000/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
checkpoint-60000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359594c8c78375e8adf65e2858c49040d246c334d6e6192f92a12b66f3db6c7b
3
+ size 1999811208
checkpoint-60000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7981479ed268cdd725ae8ca10cf9fd28e7a9d86850f00eb3e1bc5a8cc9fd0a
3
+ size 3999829471
checkpoint-60000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
3
+ size 16389
checkpoint-60000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
3
+ size 16389
checkpoint-60000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
3
+ size 16389
checkpoint-60000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
3
+ size 16389
checkpoint-60000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
3
+ size 16389
checkpoint-60000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
3
+ size 16389
checkpoint-60000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
3
+ size 16389
checkpoint-60000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
3
+ size 16389
checkpoint-60000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa47ca89507bc7bbae61946608ff1bb06ad89fb7ab56a0b42bc4222c4c9ed4af
3
+ size 1465
checkpoint-60000/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
checkpoint-60000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
checkpoint-60000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-60000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-60000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e132292bbad69e4a37b13f50b76d6466f7602cdd05b4ec3cbee9b7badde8f7
3
+ size 5841
checkpoint-70000/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_local_base_freq": 10000,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000,
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 6,
60
+ "transformers_version": "4.57.3",
61
+ "use_bidirectional_attention": false,
62
+ "use_cache": true,
63
+ "vocab_size": 262144
64
+ }
checkpoint-70000/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
checkpoint-70000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec03f805c0f2926146556449f368e7e3fa7e03bec48f1e0c1e93859275c155fa
3
+ size 1999811208
checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148afa8102018d316df473109a3d377939b7e68109c82d906ededee6c105e09f
3
+ size 3999829471
checkpoint-70000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
3
+ size 16389
checkpoint-70000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
3
+ size 16389
checkpoint-70000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
3
+ size 16389
checkpoint-70000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
3
+ size 16389
checkpoint-70000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
3
+ size 16389
checkpoint-70000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
3
+ size 16389
checkpoint-70000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
3
+ size 16389
checkpoint-70000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
3
+ size 16389
checkpoint-70000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c1e50a9dd56bfdbb20429d62a3103b0776d641a702e1daeccd096ed58f0a10
3
+ size 1465
checkpoint-70000/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
checkpoint-70000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
checkpoint-70000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-70000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-70000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e132292bbad69e4a37b13f50b76d6466f7602cdd05b4ec3cbee9b7badde8f7
3
+ size 5841
checkpoint-78125/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_local_base_freq": 10000,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000,
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 6,
60
+ "transformers_version": "4.57.3",
61
+ "use_bidirectional_attention": false,
62
+ "use_cache": true,
63
+ "vocab_size": 262144
64
+ }
checkpoint-78125/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
checkpoint-78125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823eece01510a93f6208c2a2f6eac62ea976885bbbb2a27cbe114f157234413a
3
+ size 1999811208
checkpoint-78125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b354764dc73b3c7a9d7e0b1e092dede77e0985bc8c36ef5cea82553913ca61
3
+ size 3999829471
checkpoint-78125/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
3
+ size 16389
checkpoint-78125/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
3
+ size 16389
checkpoint-78125/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
3
+ size 16389
checkpoint-78125/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
3
+ size 16389
checkpoint-78125/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
3
+ size 16389
checkpoint-78125/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
3
+ size 16389
checkpoint-78125/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
3
+ size 16389
checkpoint-78125/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
3
+ size 16389
checkpoint-78125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335c7e8b2d10447af93c2d07bd8116797d9e1b282fa764fc2e7464de0a8c6771
3
+ size 1465