Hugging Face's logo

winglian
/
reasoning-llama-3.1-70b-stratos-cold-start

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
axolotl
conversational
text-generation-inference
Model card Files
xet
Community
winglian commited on
Commit
d5c1d77
·
verified ·
1 Parent(s): bba8ab6

Add files using upload-large-folder tool

Browse files
Files changed (35) hide show
  1. README.md +154 -0
  2. axolotl/stratos.yaml +83 -0
  3. config.json +1 -1
  4. generation_config.json +1 -1
  5. model-00001-of-00030.safetensors +1 -1
  6. model-00002-of-00030.safetensors +1 -1
  7. model-00003-of-00030.safetensors +1 -1
  8. model-00004-of-00030.safetensors +1 -1
  9. model-00005-of-00030.safetensors +1 -1
  10. model-00006-of-00030.safetensors +1 -1
  11. model-00007-of-00030.safetensors +1 -1
  12. model-00008-of-00030.safetensors +1 -1
  13. model-00009-of-00030.safetensors +1 -1
  14. model-00010-of-00030.safetensors +1 -1
  15. model-00011-of-00030.safetensors +1 -1
  16. model-00012-of-00030.safetensors +1 -1
  17. model-00013-of-00030.safetensors +1 -1
  18. model-00014-of-00030.safetensors +1 -1
  19. model-00015-of-00030.safetensors +1 -1
  20. model-00016-of-00030.safetensors +1 -1
  21. model-00017-of-00030.safetensors +1 -1
  22. model-00018-of-00030.safetensors +1 -1
  23. model-00019-of-00030.safetensors +1 -1
  24. model-00020-of-00030.safetensors +1 -1
  25. model-00021-of-00030.safetensors +1 -1
  26. model-00022-of-00030.safetensors +1 -1
  27. model-00023-of-00030.safetensors +1 -1
  28. model-00024-of-00030.safetensors +1 -1
  29. model-00025-of-00030.safetensors +1 -1
  30. model-00026-of-00030.safetensors +1 -1
  31. model-00027-of-00030.safetensors +1 -1
  32. model-00028-of-00030.safetensors +1 -1
  33. model-00029-of-00030.safetensors +1 -1
  34. model-00030-of-00030.safetensors +1 -1
  35. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-70B
5
+ tags:
6
+ - generated_from_trainer
7
+ - axolotl
8
+ datasets:
9
+ - bespokelabs/Bespoke-Stratos-17k
10
+ model-index:
11
+ - name: outputs/out/reasoning-70b-stratos
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
19
+ <details><summary>See axolotl config</summary>
20
+
21
+ axolotl version: `0.8.0.dev0`
22
+ ```yaml
23
+ base_model: meta-llama/Llama-3.1-70B
24
+ # Automatically upload checkpoint and final model to HF
25
+ # hub_model_id: username/custom_model_name
26
+ #
27
+
28
+ plugins:
29
+ - axolotl.integrations.liger.LigerPlugin
30
+ - axolotl.integrations.spectrum.SpectrumPlugin
31
+ spectrum_top_fraction: 0.5
32
+ spectrum_model_name: meta-llama/Meta-Llama-3.1-70B
33
+ liger_rope: true
34
+ liger_rms_norm: true
35
+ liger_glu_activation: true
36
+ liger_fused_linear_cross_entropy: true
37
+
38
+ strict: false
39
+
40
+ chat_template: llama3
41
+ datasets:
42
+ - path: bespokelabs/Bespoke-Stratos-17k
43
+ field_messages: conversations
44
+ message_property_mappings:
45
+ content: value
46
+ role: from
47
+ split: train
48
+ type: chat_template
49
+ dataset_prepared_path: last_run_prepared
50
+ val_set_size: 0.0
51
+ output_dir: ./outputs/out/reasoning-70b-stratos
52
+ save_safetensors: true
53
+
54
+ wandb_project: reasoning-70b-stratos
55
+ wandb_entity: axolotl-ai
56
+ wandb_watch:
57
+ wandb_name:
58
+ wandb_log_model:
59
+
60
+ sequence_len: 16384
61
+ sample_packing: true
62
+ pad_to_sequence_len: true
63
+
64
+ gradient_accumulation_steps: 1
65
+ micro_batch_size: 4
66
+ num_epochs: 3
67
+ optimizer: adamw_torch_fused
68
+ lr_scheduler: rex
69
+ learning_rate: 2.0e-6
70
+ max_grad_norm: 1.0
71
+
72
+ train_on_inputs: false
73
+ group_by_length: false
74
+ bf16: true
75
+ tf32: true
76
+
77
+ gradient_checkpointing: offload
78
+ gradient_checkpointing_kwargs:
79
+ use_reentrant: true
80
+ logging_steps: 1
81
+ flash_attention: true
82
+
83
+ warmup_steps: 20
84
+ evals_per_epoch: 4
85
+ saves_per_epoch: 2
86
+ weight_decay: 0.01
87
+ deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
88
+ special_tokens:
89
+ pad_token: <|finetune_right_pad_id|>
90
+ eos_token: <|eot_id|>
91
+ added_tokens_overrides:
92
+ 128011: <think>
93
+ 128012: </think>
94
+ 128013: <|begin_of_thought|>
95
+ 128014: <|end_of_thought|>
96
+ 128015: <|begin_of_solution|>
97
+ 128016: <|end_of_solution|>
98
+ fix_untrained_tokens:
99
+ - 128011
100
+ - 128012
101
+ - 128013
102
+ - 128014
103
+ - 128015
104
+ - 128016
105
+
106
+
107
+ ```
108
+
109
+ </details><br>
110
+
111
+ # outputs/out/reasoning-70b-stratos
112
+
113
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) on the bespokelabs/Bespoke-Stratos-17k dataset.
114
+
115
+ ## Model description
116
+
117
+ More information needed
118
+
119
+ ## Intended uses & limitations
120
+
121
+ More information needed
122
+
123
+ ## Training and evaluation data
124
+
125
+ More information needed
126
+
127
+ ## Training procedure
128
+
129
+ ### Training hyperparameters
130
+
131
+ The following hyperparameters were used during training:
132
+ - learning_rate: 2e-06
133
+ - train_batch_size: 4
134
+ - eval_batch_size: 4
135
+ - seed: 42
136
+ - distributed_type: multi-GPU
137
+ - num_devices: 16
138
+ - total_train_batch_size: 64
139
+ - total_eval_batch_size: 64
140
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
141
+ - lr_scheduler_type: rex
142
+ - lr_scheduler_warmup_steps: 20
143
+ - num_epochs: 3.0
144
+
145
+ ### Training results
146
+
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - Transformers 4.49.0
152
+ - Pytorch 2.5.1+cu124
153
+ - Datasets 3.2.0
154
+ - Tokenizers 0.21.0
axolotl/stratos.yaml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: meta-llama/Llama-3.1-70B
2
+ # Automatically upload checkpoint and final model to HF
3
+ # hub_model_id: username/custom_model_name
4
+ #
5
+
6
+ plugins:
7
+ - axolotl.integrations.liger.LigerPlugin
8
+ - axolotl.integrations.spectrum.SpectrumPlugin
9
+ spectrum_top_fraction: 0.5
10
+ spectrum_model_name: meta-llama/Meta-Llama-3.1-70B
11
+ liger_rope: true
12
+ liger_rms_norm: true
13
+ liger_glu_activation: true
14
+ liger_fused_linear_cross_entropy: true
15
+
16
+ strict: false
17
+
18
+ chat_template: llama3
19
+ datasets:
20
+ - path: bespokelabs/Bespoke-Stratos-17k
21
+ field_messages: conversations
22
+ message_property_mappings:
23
+ content: value
24
+ role: from
25
+ split: train
26
+ type: chat_template
27
+ dataset_prepared_path: last_run_prepared
28
+ val_set_size: 0.0
29
+ output_dir: ./outputs/out/reasoning-70b-stratos
30
+ save_safetensors: true
31
+
32
+ wandb_project: reasoning-70b-stratos
33
+ wandb_entity: axolotl-ai
34
+ wandb_watch:
35
+ wandb_name:
36
+ wandb_log_model:
37
+
38
+ sequence_len: 16384
39
+ sample_packing: true
40
+ pad_to_sequence_len: true
41
+
42
+ gradient_accumulation_steps: 1
43
+ micro_batch_size: 4
44
+ num_epochs: 3
45
+ optimizer: adamw_torch_fused
46
+ lr_scheduler: rex
47
+ learning_rate: 2.0e-6
48
+ max_grad_norm: 1.0
49
+
50
+ train_on_inputs: false
51
+ group_by_length: false
52
+ bf16: true
53
+ tf32: true
54
+
55
+ gradient_checkpointing: offload
56
+ gradient_checkpointing_kwargs:
57
+ use_reentrant: true
58
+ logging_steps: 1
59
+ flash_attention: true
60
+
61
+ warmup_steps: 20
62
+ evals_per_epoch: 4
63
+ saves_per_epoch: 2
64
+ weight_decay: 0.01
65
+ deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
66
+ special_tokens:
67
+ pad_token: <|finetune_right_pad_id|>
68
+ eos_token: <|eot_id|>
69
+ added_tokens_overrides:
70
+ 128011: <think>
71
+ 128012: </think>
72
+ 128013: <|begin_of_thought|>
73
+ 128014: <|end_of_thought|>
74
+ 128015: <|begin_of_solution|>
75
+ 128016: <|end_of_solution|>
76
+ fix_untrained_tokens:
77
+ - 128011
78
+ - 128012
79
+ - 128013
80
+ - 128014
81
+ - 128015
82
+ - 128016
83
+
config.json CHANGED
@@ -31,6 +31,6 @@
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.49.0",
34
- "use_cache": false,
35
  "vocab_size": 128256
36
  }
 
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.49.0",
34
+ "use_cache": true,
35
  "vocab_size": 128256
36
  }
generation_config.json CHANGED
@@ -2,7 +2,7 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
- "eos_token_id": 128001,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
  "transformers_version": "4.49.0"
 
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
+ "eos_token_id": 128009,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
  "transformers_version": "4.49.0"
model-00001-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b59a526c9aa2892e04b92df1fff2763cbd365401705664d43f2148b24e89a649
3
  size 4584408808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc7b98b7522d7424f5d9a8c4511527fb917f5adf4cd405b4f203a4c020d4983
3
  size 4584408808
model-00002-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64de8e0fab8ef16f322adcb725572ea61b281b33b7eca031bbf5422f321befad
3
  size 4664167376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc17175b07d1cdd90136c0a93d94e249b10dec70ac22912276be6b42f66f3be2
3
  size 4664167376
model-00003-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f89fa445b88a7ad8197d44ef7293bc43f0d29c9a74e3032d38127b4b9514a05
3
  size 4999711704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8beb2e8315c98168b6bc811f91c946aaa93064930a490bcd41e7452faf986d2b
3
  size 4999711704
model-00004-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b69c82e1d70718c9df49c707a569c44e79772b6231d0d915af0fb9361e24154
3
  size 4966157032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c0cca3b856cb7add8f6d1751c9847a341f4525a9e047ee559793153cc3c6a73
3
  size 4966157032
model-00005-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe14d7bb6aae1a3267b539a02d8a908b3c067c0910943c0fdc85768e321cf7a6
3
  size 4664134408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04b374d990b42f97740db43db74ea5e1093d9cc6cd0d4c8155702e3a42bd435
3
  size 4664134408
model-00006-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b8dfd81dfc2d3b24d98d04cce6abdbd5209401a2364aa57a1c2e81b3adc4cb
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8039b214e68bcbaef9f4fb2b3dab38260337f43ddfde8bbf36f5da55a527d905
3
  size 4664167408
model-00007-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48091b786f90a8728d0afa01a4cd0711ac7c3e8f15b154ca2dafa0955cfceb91
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b73747b26f73e66daca0d655838669e61409923bf29c08a0745745880fb481
3
  size 4664167408
model-00008-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c19eb42c7da3b9e894283f7cfe0ed69f204607c8f71c08e6b96cd977b9d53ce
3
  size 4999711728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e2dcf4218e9ae3e25ed827729a12e1aacae68c2124694394c7f0a778c8ad4a
3
  size 4999711728
model-00009-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73ff4ba9acc51e0288d22ca4ad7e8980900c4e07ae49558444de96b3df16716c
3
  size 4966157056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a78bba2d8da6301de6d8acd0ed4cba86f0cab38a49b492c6a2a89c775be77691
3
  size 4966157056
model-00010-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f36baa37cc143314c25514bfe7ef949152b197208a9701711ff28c3dd7d13c2
3
  size 4664134408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1aa1dece387e5ecd2aecfdf3e2c14af1e5c26cc284f80598158fa3731b09022
3
  size 4664134408
model-00011-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7af63b5b1ba4f37e6ef084008638e98cf5ed63aeaaa8628deef6f57d08ddcbc9
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559ed213d9a1f666318aadd95203afdc441eee4976af81b361816d0fbee7e8fd
3
  size 4664167408
model-00012-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4137b8cdd5ec0877bc00c03b25c72d9e7a4bd96786af01d3f43ff18ee74c95b5
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d744a56d55dfdc00ef3a9ebc9d2be9bc4c06ddbf47eb6aab90e4d8dddf36dc0
3
  size 4664167408
model-00013-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:489b68e8a702e01a11d9aa09b7fe680d1808bde31f3292fe69563cfb72017067
3
  size 4999711728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbf3d8b3db3084b708bee80b1bce1a845c505de0e87c6f3dee53b5985dda229
3
  size 4999711728
model-00014-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d820508dc7f414480e031c41f9f68f2ac9c03851bc1bcce92862ac4b3e66a0b3
3
  size 4966157056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c942c785d84fefe4dc237ff244d27701a5ffe9f677ea095680f2932ee98dbeaf
3
  size 4966157056
model-00015-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f5aa4b3d015d4ef45edf774d8ba0150c8a2d743591957d5375eeb5affda0f89
3
  size 4664134408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80ec14ac958d9f4d96b943882ab1a83ed8e575ffed6d3b18392a0cf14741edf
3
  size 4664134408
model-00016-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82cf2b9e73c3307a58e09a9d232440c7729a231e8a3967b6d47797fad942ac93
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ac4c897760b2e53ddc9cccb75c2bff1d178ba82429f709295a607c62170dfc
3
  size 4664167408
model-00017-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e5f1638dae564b128a6b959c9715a533041e2fc33e9d3cd91b20c77f8968902
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01bcd4f1135f1b169765cb787d4f0b632f066b6b34b46abf12812c74bfb188ae
3
  size 4664167408
model-00018-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42063a50e0c399c40839be0d3a7a2499c09bcecb773da72f42edab37b5856de2
3
  size 4999711728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9ebc10f2213e68fecc7948c759623df31b2553d344cac65b67136d248336fd
3
  size 4999711728
model-00019-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65501f1bf489f180e1a2e7d5a279997c09b8097fbe6c3af590856948788660a9
3
  size 4966157056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257faaf17421bdbf96ce474ca32bfc0f1c09bb95a18fc7e79cc61923df1c6f4a
3
  size 4966157056
model-00020-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8948c2be3b42021e1326361e2d295398fefa73148925dae08e01e1666896d86d
3
  size 4664134408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852e5d26dc312522d746d00f7aa00295c64e271e7d01740c2a9d3f95bfb8d5a2
3
  size 4664134408
model-00021-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e852af5c8e47f9ab67f7a2da839f267ac4447bf421551f533e62af53f376ad7a
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccbe9309d606f0586f52f19ac6edd7f48f3b544aa5247407d9b1ec91731afa1
3
  size 4664167408
model-00022-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8e5722fd520032f80f8d6d3b3a72393d140a29f6367f50d55991a73b0df9192
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304bc52da148a550f3da05ca4c93022968da605798408d97578cc2364c093d45
3
  size 4664167408
model-00023-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaa144c7b189511506b21947124a5be008594c53fcafa106361eadb1bc383623
3
  size 4999711728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e28b06a3916ed162cdbfa6a72b78cb5fbce0b95b8f9abe9d9618e0b881f4ab
3
  size 4999711728
model-00024-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38812b559533395d489a7aa671b0a9e92ae0fe681eec063868038e6f6e6564a2
3
  size 4966157056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7815109f69efed0ae5fb5979e926129b9a191c2d93a86e95ea7720bc919b545
3
  size 4966157056
model-00025-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeda9ff853df0b9d556b0bb59bbe3289d7eb9e07c281a51952cc62fa32d89ecf
3
  size 4664134408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5269083fa70b4c3adf1fda159ad34738a43ea9480cad60ad4a4d02d693106a6f
3
  size 4664134408
model-00026-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0211268ff17fa3913fc093f936da41f6622bce92220a6677f883f0ece0ad3618
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198039c00faf863c73ef6f38f7d40d2d40f34139d360e7ca8a72361b7d1b86e9
3
  size 4664167408
model-00027-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4b79457b4ca5bfb61d37cce3a3274e682a88effd7b0d8bb27add227ce4dc872
3
  size 4664167408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3704750548c4d689addd041ee0740144f074cad571054292df1ad1da6ab036d
3
  size 4664167408
model-00028-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924bce60cfa093a26fdb7fb416e3550b47c8fa81ff22af2999801e8023c5ab80
3
  size 4999711728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae32f673ba22a34c2faea31844f6a7287323246d7285684c14199ad6b5f6da6
3
  size 4999711728
model-00029-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d273b022faf4870764e057a753c45d3d8ae8a7e391c9d700b4cb75aa2a2f176f
3
  size 4966173536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd49561abfdc0bda3bb7a7669170e63f9c04e5b440b9b1c5474a98036f8cf7a
3
  size 4966173536
model-00030-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7295244634d7607230ef14c8ec53879b18e0de1a5512a53dfafe858fcf32976d
3
  size 2101346432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccca7dd64397d52d7a306f14db6ab7f9604075368275818fad4c10fea8f4c2d
3
  size 2101346432
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a77d6d91546c39d9bb5cbb150b96772783d97bb43be2593ca79b74147e2a329
3
+ size 9144