Hugging Face's logo

aixk
/
twiny-stack-L01

Text Generation
ONNX
Safetensors
twiny
Model card Files
xet
 Community
aixk commited on
Commit
886c52a
·
verified ·
1 Parent(s): be1030a

final purge backups 1/1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. shared/auto_workers/twiny-stack-L01/worker-1889d6ba.json +0 -1
  2. shared/auto_workers/twiny-stack-L01/worker-1c621c3b.json +0 -1
  3. shared/auto_workers/twiny-stack-L01/worker-2d3af221.json +0 -1
  4. shared/auto_workers/twiny-stack-L01/worker-2de8ee97.json +0 -1
  5. shared/auto_workers/twiny-stack-L01/worker-32cedafe.json +0 -1
  6. shared/auto_workers/twiny-stack-L01/worker-39799582.json +0 -1
  7. shared/auto_workers/twiny-stack-L01/worker-437ed89a.json +0 -1
  8. shared/auto_workers/twiny-stack-L01/worker-4f6f9a42.json +0 -1
  9. shared/auto_workers/twiny-stack-L01/worker-5c63816b.json +0 -1
  10. shared/auto_workers/twiny-stack-L01/worker-6703a54a.json +0 -1
  11. shared/auto_workers/twiny-stack-L01/worker-678fe5b4.json +0 -1
  12. shared/auto_workers/twiny-stack-L01/worker-68562547.json +0 -1
  13. shared/auto_workers/twiny-stack-L01/worker-6b2dd25a.json +0 -1
  14. shared/auto_workers/twiny-stack-L01/worker-72607007.json +0 -1
  15. shared/auto_workers/twiny-stack-L01/worker-759f01b2.json +0 -1
  16. shared/auto_workers/twiny-stack-L01/worker-78931474.json +0 -1
  17. shared/auto_workers/twiny-stack-L01/worker-7be76f00.json +0 -1
  18. shared/auto_workers/twiny-stack-L01/worker-82f8ac64.json +0 -1
  19. shared/auto_workers/twiny-stack-L01/worker-831fbd8b.json +0 -1
  20. shared/auto_workers/twiny-stack-L01/worker-85cf7528.json +0 -1
  21. shared/auto_workers/twiny-stack-L01/worker-88c03ef3.json +0 -1
  22. shared/auto_workers/twiny-stack-L01/worker-8d6cedf8.json +0 -1
  23. shared/auto_workers/twiny-stack-L01/worker-9bd051d5.json +0 -1
  24. shared/auto_workers/twiny-stack-L01/worker-a7264add.json +0 -1
  25. shared/auto_workers/twiny-stack-L01/worker-ab62f0b2.json +0 -1
  26. shared/auto_workers/twiny-stack-L01/worker-af14b97c.json +0 -1
  27. shared/auto_workers/twiny-stack-L01/worker-af57f599.json +0 -1
  28. shared/auto_workers/twiny-stack-L01/worker-afb39a74.json +0 -1
  29. shared/auto_workers/twiny-stack-L01/worker-b5df3b83.json +0 -1
  30. shared/auto_workers/twiny-stack-L01/worker-b6d1042e.json +0 -1
  31. shared/auto_workers/twiny-stack-L01/worker-c4b1a0c1.json +0 -1
  32. shared/auto_workers/twiny-stack-L01/worker-ec6532b5.json +0 -1
  33. shared/auto_workers/twiny-stack-L01/worker-f12ecd82.json +0 -1
  34. shared/auto_workers/twiny-stack-L01/worker-f88aef85.json +0 -1
  35. shared/auto_workers/twiny-stack-L01/worker-f9429d7f.json +0 -1
  36. shared/auto_workers/twiny-stack-L01/worker-fa5b7284.json +0 -1
  37. shared/global/merged/config.json +0 -24
  38. shared/global/merged/merge_info.json +0 -1
  39. shared/global/merged/model.safetensors +0 -3
  40. shared/global/merged/tokenizer.json +0 -0
  41. shared/global/merged/tokenizer_config.json +0 -15
  42. shared/slot_plan/twiny-stack-L01/stage1.json +0 -1
  43. workers/worker-2de8ee97/final/config.json +0 -24
  44. workers/worker-2de8ee97/final/tokenizer.json +0 -0
  45. workers/worker-2de8ee97/final/tokenizer_config.json +0 -15
  46. workers/worker-2de8ee97/final_meta.json +0 -1
  47. workers/worker-5c63816b/final/config.json +0 -24
  48. workers/worker-5c63816b/final/tokenizer.json +0 -0
  49. workers/worker-5c63816b/final/tokenizer_config.json +0 -15
  50. workers/worker-5c63816b/final_meta.json +0 -1
shared/auto_workers/twiny-stack-L01/worker-1889d6ba.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-1889d6ba", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776402701}
 
 
shared/auto_workers/twiny-stack-L01/worker-1c621c3b.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-1c621c3b", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776344797}
 
 
shared/auto_workers/twiny-stack-L01/worker-2d3af221.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-2d3af221", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776402753}
 
 
shared/auto_workers/twiny-stack-L01/worker-2de8ee97.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-2de8ee97", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413958}
 
 
shared/auto_workers/twiny-stack-L01/worker-32cedafe.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-32cedafe", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776389057}
 
 
shared/auto_workers/twiny-stack-L01/worker-39799582.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-39799582", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401336}
 
 
shared/auto_workers/twiny-stack-L01/worker-437ed89a.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-437ed89a", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776389057}
 
 
shared/auto_workers/twiny-stack-L01/worker-4f6f9a42.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-4f6f9a42", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401338}
 
 
shared/auto_workers/twiny-stack-L01/worker-5c63816b.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-5c63816b", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413953}
 
 
shared/auto_workers/twiny-stack-L01/worker-6703a54a.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-6703a54a", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401334}
 
 
shared/auto_workers/twiny-stack-L01/worker-678fe5b4.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-678fe5b4", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413956}
 
 
shared/auto_workers/twiny-stack-L01/worker-68562547.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-68562547", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401335}
 
 
shared/auto_workers/twiny-stack-L01/worker-6b2dd25a.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-6b2dd25a", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776385422}
 
 
shared/auto_workers/twiny-stack-L01/worker-72607007.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-72607007", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401335}
 
 
shared/auto_workers/twiny-stack-L01/worker-759f01b2.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-759f01b2", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776348363}
 
 
shared/auto_workers/twiny-stack-L01/worker-78931474.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-78931474", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776347084}
 
 
shared/auto_workers/twiny-stack-L01/worker-7be76f00.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-7be76f00", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776344794}
 
 
shared/auto_workers/twiny-stack-L01/worker-82f8ac64.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-82f8ac64", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401341}
 
 
shared/auto_workers/twiny-stack-L01/worker-831fbd8b.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-831fbd8b", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776389080}
 
 
shared/auto_workers/twiny-stack-L01/worker-85cf7528.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-85cf7528", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776345736}
 
 
shared/auto_workers/twiny-stack-L01/worker-88c03ef3.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-88c03ef3", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776386026}
 
 
shared/auto_workers/twiny-stack-L01/worker-8d6cedf8.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-8d6cedf8", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776389065}
 
 
shared/auto_workers/twiny-stack-L01/worker-9bd051d5.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-9bd051d5", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401345}
 
 
shared/auto_workers/twiny-stack-L01/worker-a7264add.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-a7264add", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401334}
 
 
shared/auto_workers/twiny-stack-L01/worker-ab62f0b2.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-ab62f0b2", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776347092}
 
 
shared/auto_workers/twiny-stack-L01/worker-af14b97c.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-af14b97c", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776345735}
 
 
shared/auto_workers/twiny-stack-L01/worker-af57f599.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-af57f599", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776402742}
 
 
shared/auto_workers/twiny-stack-L01/worker-afb39a74.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-afb39a74", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776348365}
 
 
shared/auto_workers/twiny-stack-L01/worker-b5df3b83.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-b5df3b83", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776345735}
 
 
shared/auto_workers/twiny-stack-L01/worker-b6d1042e.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-b6d1042e", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776389060}
 
 
shared/auto_workers/twiny-stack-L01/worker-c4b1a0c1.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-c4b1a0c1", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413957}
 
 
shared/auto_workers/twiny-stack-L01/worker-ec6532b5.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-ec6532b5", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413955}
 
 
shared/auto_workers/twiny-stack-L01/worker-f12ecd82.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-f12ecd82", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776402709}
 
 
shared/auto_workers/twiny-stack-L01/worker-f88aef85.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-f88aef85", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776344796}
 
 
shared/auto_workers/twiny-stack-L01/worker-f9429d7f.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-f9429d7f", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776413958}
 
 
shared/auto_workers/twiny-stack-L01/worker-fa5b7284.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-fa5b7284", "stage": 1, "model_name": "twiny-stack-L01", "updated_at": 1776401340}
 
 
shared/global/merged/config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "architectures": [
3
- "TwinyForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "dtype": "float32",
7
- "hidden_dropout": 0.0,
8
- "hidden_size": 768,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 3072,
11
- "max_position_embeddings": 128,
12
- "model_type": "twiny",
13
- "neftune_alpha": 0.0,
14
- "num_attention_heads": 12,
15
- "num_hidden_layers": 1,
16
- "num_key_value_heads": 3,
17
- "qk_norm": true,
18
- "rezero_init": 1.0,
19
- "rms_norm_eps": 1e-06,
20
- "rope_theta": 10000.0,
21
- "transformers_version": "5.0.0",
22
- "use_cache": false,
23
- "vocab_size": 32000
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
shared/global/merged/merge_info.json DELETED
@@ -1 +0,0 @@
1
- {"workers": ["worker-678fe5b4", "worker-ec6532b5", "worker-2de8ee97"], "weights": [229269.0, 229269.0, 305691.0], "merged_count": 3, "updated_at": 1776418038}
 
 
shared/global/merged/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e801380795cc1c04820af9b8d016adba35c6c07255e562b154af54719530fff4
3
- size 233203620
 
 
 
 
shared/global/merged/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
shared/global/merged/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<bos>",
4
- "clean_up_tokenization_spaces": false,
5
- "eos_token": "<eos>",
6
- "extra_special_tokens": [
7
- "<|im_start|>",
8
- "<|im_end|>"
9
- ],
10
- "is_local": true,
11
- "model_max_length": 1000000,
12
- "pad_token": "<pad>",
13
- "tokenizer_class": "TokenizersBackend",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
shared/slot_plan/twiny-stack-L01/stage1.json DELETED
@@ -1 +0,0 @@
1
- {"model_name": "twiny-stack-L01", "stage": 1, "slot_total": 20, "worker_id": "worker-ec6532b5", "updated_at": 1776414199, "slot_workers": ["worker-9bd051d5", "worker-82f8ac64", "worker-fa5b7284", "worker-4f6f9a42", "worker-39799582", "worker-68562547", "worker-72607007", "worker-6703a54a", "worker-a7264add", "worker-2d3af221", "worker-af57f599", "worker-f12ecd82", "worker-1889d6ba", "worker-2de8ee97", "worker-f9429d7f", "worker-c4b1a0c1", "worker-678fe5b4", "worker-ec6532b5", "worker-5c63816b"]}
 
 
workers/worker-2de8ee97/final/config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "architectures": [
3
- "TwinyForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "dtype": "float32",
7
- "hidden_dropout": 0.0,
8
- "hidden_size": 768,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 3072,
11
- "max_position_embeddings": 128,
12
- "model_type": "twiny",
13
- "neftune_alpha": 0.0,
14
- "num_attention_heads": 12,
15
- "num_hidden_layers": 1,
16
- "num_key_value_heads": 3,
17
- "qk_norm": true,
18
- "rezero_init": 1.0,
19
- "rms_norm_eps": 1e-06,
20
- "rope_theta": 10000.0,
21
- "transformers_version": "5.0.0",
22
- "use_cache": false,
23
- "vocab_size": 32000
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
workers/worker-2de8ee97/final/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
workers/worker-2de8ee97/final/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<bos>",
4
- "clean_up_tokenization_spaces": false,
5
- "eos_token": "<eos>",
6
- "extra_special_tokens": [
7
- "<|im_start|>",
8
- "<|im_end|>"
9
- ],
10
- "is_local": true,
11
- "model_max_length": 1000000,
12
- "pad_token": "<pad>",
13
- "tokenizer_class": "TokenizersBackend",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
workers/worker-2de8ee97/final_meta.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-2de8ee97", "model_name": "twiny-stack-L01", "train_blocks": 305691, "worker_index": 0, "total_workers": 6, "updated_at": 1776417995}
 
 
workers/worker-5c63816b/final/config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "architectures": [
3
- "TwinyForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "dtype": "float32",
7
- "hidden_dropout": 0.0,
8
- "hidden_size": 768,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 3072,
11
- "max_position_embeddings": 128,
12
- "model_type": "twiny",
13
- "neftune_alpha": 0.0,
14
- "num_attention_heads": 12,
15
- "num_hidden_layers": 1,
16
- "num_key_value_heads": 3,
17
- "qk_norm": true,
18
- "rezero_init": 1.0,
19
- "rms_norm_eps": 1e-06,
20
- "rope_theta": 10000.0,
21
- "transformers_version": "5.0.0",
22
- "use_cache": false,
23
- "vocab_size": 32000
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
workers/worker-5c63816b/final/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
workers/worker-5c63816b/final/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<bos>",
4
- "clean_up_tokenization_spaces": false,
5
- "eos_token": "<eos>",
6
- "extra_special_tokens": [
7
- "<|im_start|>",
8
- "<|im_end|>"
9
- ],
10
- "is_local": true,
11
- "model_max_length": 1000000,
12
- "pad_token": "<pad>",
13
- "tokenizer_class": "TokenizersBackend",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
workers/worker-5c63816b/final_meta.json DELETED
@@ -1 +0,0 @@
1
- {"worker_id": "worker-5c63816b", "model_name": "twiny-stack-L01", "train_blocks": 229269, "worker_index": 5, "total_workers": 6, "updated_at": 1776418006}