Hugging Face's logo

ambivalent02
/
pretrained_elvis_lfm

Safetensors
lfm2
Model card Files
xet
 Community
ambivalent02 commited on
Commit
ac3dec5
·
verified ·
1 Parent(s): 7bad98e

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +37 -0
  3. config.json +91 -0
  4. generation_config.json +9 -0
  5. global_step128000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  6. global_step128000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  7. global_step128000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
  8. global_step128000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  9. global_step128000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
  10. global_step128000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  11. global_step128000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  12. global_step128000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  13. global_step128000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  14. global_step128000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  15. global_step128000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  16. global_step128000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  17. global_step128000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  18. global_step128000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  19. global_step128000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
  20. global_step128000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  21. global_step128000/mp_rank_00_model_states.pt +3 -0
  22. latest +1 -0
  23. model.safetensors +3 -0
  24. rng_state_0.pth +3 -0
  25. rng_state_1.pth +3 -0
  26. rng_state_10.pth +3 -0
  27. rng_state_11.pth +3 -0
  28. rng_state_12.pth +3 -0
  29. rng_state_13.pth +3 -0
  30. rng_state_14.pth +3 -0
  31. rng_state_15.pth +3 -0
  32. rng_state_2.pth +3 -0
  33. rng_state_3.pth +3 -0
  34. rng_state_4.pth +3 -0
  35. rng_state_5.pth +3 -0
  36. rng_state_6.pth +3 -0
  37. rng_state_7.pth +3 -0
  38. rng_state_8.pth +3 -0
  39. rng_state_9.pth +3 -0
  40. scheduler.pt +3 -0
  41. special_tokens_map.json +23 -0
  42. tokenizer.json +0 -0
  43. tokenizer_config.json +4079 -0
  44. trainer_state.json +3 -0
  45. training_args.bin +3 -0
  46. zero_to_fp32.py +760 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set system_prompt = "" -%}
3
+ {%- set ns = namespace(system_prompt="") -%}
4
+ {%- if messages[0]["role"] == "system" -%}
5
+ {%- set ns.system_prompt = messages[0]["content"] -%}
6
+ {%- set messages = messages[1:] -%}
7
+ {%- endif -%}
8
+ {%- if tools -%}
9
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
10
+ {%- for tool in tools -%}
11
+ {%- if tool is not string -%}
12
+ {%- set tool = tool | tojson -%}
13
+ {%- endif -%}
14
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
15
+ {%- if not loop.last -%}
16
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
17
+ {%- endif -%}
18
+ {%- endfor -%}
19
+ {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
20
+ {%- endif -%}
21
+ {%- if ns.system_prompt -%}
22
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
23
+ {%- endif -%}
24
+ {%- for message in messages -%}
25
+ {{- "<|im_start|>" + message["role"] + "\n" -}}
26
+ {%- set content = message["content"] -%}
27
+ {%- if content is not string -%}
28
+ {%- set content = content | tojson -%}
29
+ {%- endif -%}
30
+ {%- if message["role"] == "tool" -%}
31
+ {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
32
+ {%- endif -%}
33
+ {{- content + "<|im_end|>\n" -}}
34
+ {%- endfor -%}
35
+ {%- if add_generation_prompt -%}
36
+ {{- "<|im_start|>assistant\n" -}}
37
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_faster_video": false,
3
+ "add_time_instruction": false,
4
+ "architectures": [
5
+ "LlavaLfm2ForCausalLM"
6
+ ],
7
+ "block_auto_adjust_ff_dim": true,
8
+ "block_dim": 1024,
9
+ "block_ff_dim": 6656,
10
+ "block_ffn_dim_multiplier": 1.0,
11
+ "block_mlp_init_scale": 1.0,
12
+ "block_multiple_of": 256,
13
+ "block_norm_eps": 1e-05,
14
+ "block_out_init_scale": 1.0,
15
+ "block_use_swiglu": true,
16
+ "block_use_xavier_init": true,
17
+ "bos_token_id": 1,
18
+ "conv_L_cache": 3,
19
+ "conv_bias": false,
20
+ "conv_dim": 1024,
21
+ "conv_dim_out": 1024,
22
+ "conv_use_xavier_init": true,
23
+ "dtype": "bfloat16",
24
+ "eos_token_id": 7,
25
+ "faster_token_stride": 10,
26
+ "force_sample": false,
27
+ "hidden_size": 1024,
28
+ "image_aspect_ratio": "convnext",
29
+ "image_crop_resolution": null,
30
+ "image_grid_pinpoints": null,
31
+ "image_split_resolution": null,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 6656,
34
+ "layer_types": [
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "full_attention",
41
+ "conv",
42
+ "conv",
43
+ "full_attention",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "full_attention",
48
+ "conv",
49
+ "full_attention",
50
+ "conv"
51
+ ],
52
+ "max_position_embeddings": 128000,
53
+ "mm_hidden_size": 1024,
54
+ "mm_newline_position": "grid",
55
+ "mm_patch_merge_type": "flat",
56
+ "mm_projector_lr": 1e-06,
57
+ "mm_projector_type": "layernorm",
58
+ "mm_resampler_type": "minicpm",
59
+ "mm_spatial_pool_mode": "bilinear",
60
+ "mm_spatial_pool_out_channels": null,
61
+ "mm_spatial_pool_stride": null,
62
+ "mm_tunable_parts": "mm_mlp_adapter, mm_vision_tower,mm_language_model, mm_vision_resampler",
63
+ "mm_use_im_patch_token": false,
64
+ "mm_use_im_start_end": false,
65
+ "mm_vision_resolution": 256,
66
+ "mm_vision_select_feature": "patch",
67
+ "mm_vision_select_layer": -1,
68
+ "mm_vision_tower": "/lustre/scratch/client/movian/research/users/chitb/ELVIS_SAVE_MODELS/converted_convnext_base_w_320",
69
+ "mm_vision_tower_lr": 1e-06,
70
+ "model_type": "lfm2",
71
+ "norm_eps": 1e-05,
72
+ "num_attention_heads": 16,
73
+ "num_heads": 16,
74
+ "num_hidden_layers": 16,
75
+ "num_key_value_heads": 8,
76
+ "pad_token_id": 0,
77
+ "pos_skipping_range": 4096,
78
+ "rope_scaling": null,
79
+ "rope_theta": 1000000.0,
80
+ "tokenizer_model_max_length": 8192,
81
+ "tokenizer_padding_side": "right",
82
+ "transformers_version": "4.56.2",
83
+ "use_cache": false,
84
+ "use_mm_proj": true,
85
+ "use_pos_enc": true,
86
+ "use_pos_skipping": false,
87
+ "vision_add_five_stage": 0,
88
+ "vision_five_stage_width": 1024,
89
+ "vision_tower_pretrained": null,
90
+ "vocab_size": 65536
91
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 7
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.56.2"
9
+ }
global_step128000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad1aad468ae261656421c118c655f7d87e88ec8789dc3a89878976a9a7e6619
3
+ size 337084179
global_step128000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88cea427d6ac6fcb9052ea39a363231da114d8f8b5a4ec324a8df0f9a1f0a4e
3
+ size 337079921
global_step128000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0803f0d7681d130f6ecffe778cd7a4de77be19c97bf9892521b70c7616788ad4
3
+ size 337079665
global_step128000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8e387035211739cb48381bc028c0a86c3ae4b29a0036d2d926751f286e0054
3
+ size 337079601
global_step128000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5fb0b5d75eb2c74ce6d706413e6b3cadf3f52af085fbe1e5663220d6d5a38d
3
+ size 337078385
global_step128000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd862ad5afd8b19f5fedccc208b351396a1a74f090156a59e4e7ac799bbf74c
3
+ size 337079025
global_step128000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743ecebb9917f9d79a34716dd53f4e0d28ee3d9cdca740ed5476dfcbd92ae830
3
+ size 337078385
global_step128000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3da6db11aa119992606fb9b1ddb003eea6ddff5cf572c38a31dad1c02154eb
3
+ size 337079251
global_step128000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4affbf26252d7c9a992cd169531cd6108d29ce99aef13ada39ff8ce3d29c107d
3
+ size 337079571
global_step128000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ca9561d3e3d21f9573b2a4dfea86fcc1b5db27006eb034fac1727b16480511
3
+ size 337080211
global_step128000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40f969b9d01c015d30d883a9ddd61ecc29e2252be8bc4435e77c2472a166def
3
+ size 337079955
global_step128000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a230892f27530ab39490b9de86cc0ffb7c9c13e16f331fcbd5862d590a5819
3
+ size 337080019
global_step128000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20054dc12d659223e611a227fa33f8d5005104ca0dac15901c4a21890bb4cf6a
3
+ size 337079827
global_step128000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13cccf9fe5b1a9dc112877c48e8c26e425aea61151ff5f8fd370fb12bfddda1
3
+ size 337080595
global_step128000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c798b44f8abba2d553bd00dc4bbcc964264429fbf7bd8e4c444896aef9cfa4f4
3
+ size 337079635
global_step128000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31356b419adcd98eefed1d96d70c16c9800b1d076977d15eb89327293609c683
3
+ size 337080467
global_step128000/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5971caa8844a5d3cc5d014285add6d0bd29d08d26510c87dcca8fbcb05dbcca
3
+ size 899010325
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step128000
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9e9a817dac658ed68efe08a8dc260acc6a8873baff22d5226bd069760eb21d0
3
+ size 1033128352
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478b41e9f26d338fd8f896e08cad1adab7c423b61f1b45754113bc78d256a3f9
3
+ size 16389
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
3
+ size 16389
rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4087d2ea47662689d49bb2a193a439cc647f4bf7661c0699b634d2580d8ed1
3
+ size 16404
rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd6d14b9cf8fda11fa20ad63ce180ed2c55a6863be6f70a470ce36db04d514a5
3
+ size 16404
rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73b211a7c9d122d2d22f4ff6334556d3e848d9388e6d61a53984bad28d01625
3
+ size 16404
rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1921c842a450f0dc72f9fd7bdb969c0e513cd8394cb13b6a07e0f39dc1a8c1
3
+ size 16404
rng_state_14.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b0133cf52a51748bbdb12aef4160adb88f185be360750b706782d04b72b45b
3
+ size 16404
rng_state_15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da6499a7936a7581567e9bd841bb4577ba1e29a68c1a807e46cfca70f5a7154
3
+ size 16404
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
3
+ size 16389
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
3
+ size 16389
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
3
+ size 16389
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
3
+ size 16389
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
3
+ size 16389
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
3
+ size 16389
rng_state_8.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e28f7e443dd9c70af7dee145284e83b9ae7c3f767c68e9c7f00b5735c44d7a
3
+ size 16389
rng_state_9.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3deb356998c7ff5b30cb2b38f4c2a6867400bf7db6468d1e1ab12e37a3a9662e
3
+ size 16389
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b358e0fc94e117f7f62e2deb7bf15daf3d508121b658725d8b0fb430af91e6
3
+ size 1529
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,4079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|fim_pre|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|fim_mid|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|fim_suf|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|im_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|im_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|tool_list_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|tool_list_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|tool_call_start|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|tool_call_end|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|tool_response_start|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|tool_response_end|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "16": {
118
+ "content": "<|reserved_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "17": {
126
+ "content": "<|reserved_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "18": {
134
+ "content": "<|reserved_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "19": {
142
+ "content": "<|reserved_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "20": {
150
+ "content": "<|reserved_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "21": {
158
+ "content": "<|reserved_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "22": {
166
+ "content": "<|reserved_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "23": {
174
+ "content": "<|reserved_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "24": {
182
+ "content": "<|reserved_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "25": {
190
+ "content": "<|reserved_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "26": {
198
+ "content": "<|reserved_16|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "27": {
206
+ "content": "<|reserved_17|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "28": {
214
+ "content": "<|reserved_18|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "29": {
222
+ "content": "<|reserved_19|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "30": {
230
+ "content": "<|reserved_20|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "31": {
238
+ "content": "<|reserved_21|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32": {
246
+ "content": "<|reserved_22|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "33": {
254
+ "content": "<|reserved_23|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "34": {
262
+ "content": "<|reserved_24|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "35": {
270
+ "content": "<|reserved_25|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "36": {
278
+ "content": "<|reserved_26|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "37": {
286
+ "content": "<|reserved_27|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "38": {
294
+ "content": "<|reserved_28|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "39": {
302
+ "content": "<|reserved_29|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "40": {
310
+ "content": "<|reserved_30|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "41": {
318
+ "content": "<|reserved_31|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "42": {
326
+ "content": "<|reserved_32|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "43": {
334
+ "content": "<|reserved_33|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "44": {
342
+ "content": "<|reserved_34|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "45": {
350
+ "content": "<|reserved_35|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "46": {
358
+ "content": "<|reserved_36|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "47": {
366
+ "content": "<|reserved_37|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "48": {
374
+ "content": "<|reserved_38|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "49": {
382
+ "content": "<|reserved_39|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "50": {
390
+ "content": "<|reserved_40|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "51": {
398
+ "content": "<|reserved_41|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "52": {
406
+ "content": "<|reserved_42|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "53": {
414
+ "content": "<|reserved_43|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "54": {
422
+ "content": "<|reserved_44|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "55": {
430
+ "content": "<|reserved_45|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "56": {
438
+ "content": "<|reserved_46|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "57": {
446
+ "content": "<|reserved_47|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "58": {
454
+ "content": "<|reserved_48|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "59": {
462
+ "content": "<|reserved_49|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "60": {
470
+ "content": "<|reserved_50|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "61": {
478
+ "content": "<|reserved_51|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "62": {
486
+ "content": "<|reserved_52|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "63": {
494
+ "content": "<|reserved_53|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "64": {
502
+ "content": "<|reserved_54|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "65": {
510
+ "content": "<|reserved_55|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "66": {
518
+ "content": "<|reserved_56|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "67": {
526
+ "content": "<|reserved_57|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "68": {
534
+ "content": "<|reserved_58|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "69": {
542
+ "content": "<|reserved_59|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "70": {
550
+ "content": "<|reserved_60|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "71": {
558
+ "content": "<|reserved_61|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "72": {
566
+ "content": "<|reserved_62|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "73": {
574
+ "content": "<|reserved_63|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "74": {
582
+ "content": "<|reserved_64|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "75": {
590
+ "content": "<|reserved_65|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "76": {
598
+ "content": "<|reserved_66|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "77": {
606
+ "content": "<|reserved_67|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "78": {
614
+ "content": "<|reserved_68|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "79": {
622
+ "content": "<|reserved_69|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "80": {
630
+ "content": "<|reserved_70|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "81": {
638
+ "content": "<|reserved_71|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "82": {
646
+ "content": "<|reserved_72|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "83": {
654
+ "content": "<|reserved_73|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "84": {
662
+ "content": "<|reserved_74|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "85": {
670
+ "content": "<|reserved_75|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "86": {
678
+ "content": "<|reserved_76|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "87": {
686
+ "content": "<|reserved_77|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "88": {
694
+ "content": "<|reserved_78|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "89": {
702
+ "content": "<|reserved_79|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "90": {
710
+ "content": "<|reserved_80|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "91": {
718
+ "content": "<|reserved_81|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "92": {
726
+ "content": "<|reserved_82|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "93": {
734
+ "content": "<|reserved_83|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "94": {
742
+ "content": "<|reserved_84|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "95": {
750
+ "content": "<|reserved_85|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "96": {
758
+ "content": "<|reserved_86|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "97": {
766
+ "content": "<|reserved_87|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "98": {
774
+ "content": "<|reserved_88|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "99": {
782
+ "content": "<|reserved_89|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "100": {
790
+ "content": "<|reserved_90|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "101": {
798
+ "content": "<|reserved_91|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "102": {
806
+ "content": "<|reserved_92|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "103": {
814
+ "content": "<|reserved_93|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "104": {
822
+ "content": "<|reserved_94|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "105": {
830
+ "content": "<|reserved_95|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "106": {
838
+ "content": "<|reserved_96|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "107": {
846
+ "content": "<|reserved_97|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "108": {
854
+ "content": "<|reserved_98|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "109": {
862
+ "content": "<|reserved_99|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "110": {
870
+ "content": "<|reserved_100|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "111": {
878
+ "content": "<|reserved_101|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "112": {
886
+ "content": "<|reserved_102|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "113": {
894
+ "content": "<|reserved_103|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "114": {
902
+ "content": "<|reserved_104|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "115": {
910
+ "content": "<|reserved_105|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "116": {
918
+ "content": "<|reserved_106|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "117": {
926
+ "content": "<|reserved_107|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "118": {
934
+ "content": "<|reserved_108|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "119": {
942
+ "content": "<|reserved_109|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "120": {
950
+ "content": "<|reserved_110|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "121": {
958
+ "content": "<|reserved_111|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "122": {
966
+ "content": "<|reserved_112|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "123": {
974
+ "content": "<|reserved_113|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "124": {
982
+ "content": "<|reserved_114|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "125": {
990
+ "content": "<|reserved_115|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "126": {
998
+ "content": "<|reserved_116|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "127": {
1006
+ "content": "<|reserved_117|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "128": {
1014
+ "content": "<|reserved_118|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "129": {
1022
+ "content": "<|reserved_119|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "130": {
1030
+ "content": "<|reserved_120|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "131": {
1038
+ "content": "<|reserved_121|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "132": {
1046
+ "content": "<|reserved_122|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "133": {
1054
+ "content": "<|reserved_123|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "134": {
1062
+ "content": "<|reserved_124|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "135": {
1070
+ "content": "<|reserved_125|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "136": {
1078
+ "content": "<|reserved_126|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "137": {
1086
+ "content": "<|reserved_127|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "138": {
1094
+ "content": "<|reserved_128|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "139": {
1102
+ "content": "<|reserved_129|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "140": {
1110
+ "content": "<|reserved_130|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "141": {
1118
+ "content": "<|reserved_131|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "142": {
1126
+ "content": "<|reserved_132|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "143": {
1134
+ "content": "<|reserved_133|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "144": {
1142
+ "content": "<|reserved_134|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "145": {
1150
+ "content": "<|reserved_135|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "146": {
1158
+ "content": "<|reserved_136|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "147": {
1166
+ "content": "<|reserved_137|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "148": {
1174
+ "content": "<|reserved_138|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "149": {
1182
+ "content": "<|reserved_139|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "150": {
1190
+ "content": "<|reserved_140|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151": {
1198
+ "content": "<|reserved_141|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "152": {
1206
+ "content": "<|reserved_142|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "153": {
1214
+ "content": "<|reserved_143|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "154": {
1222
+ "content": "<|reserved_144|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "155": {
1230
+ "content": "<|reserved_145|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "156": {
1238
+ "content": "<|reserved_146|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "157": {
1246
+ "content": "<|reserved_147|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "158": {
1254
+ "content": "<|reserved_148|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "159": {
1262
+ "content": "<|reserved_149|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "160": {
1270
+ "content": "<|reserved_150|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "161": {
1278
+ "content": "<|reserved_151|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "162": {
1286
+ "content": "<|reserved_152|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "163": {
1294
+ "content": "<|reserved_153|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "164": {
1302
+ "content": "<|reserved_154|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "165": {
1310
+ "content": "<|reserved_155|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "166": {
1318
+ "content": "<|reserved_156|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "167": {
1326
+ "content": "<|reserved_157|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "168": {
1334
+ "content": "<|reserved_158|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "169": {
1342
+ "content": "<|reserved_159|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "170": {
1350
+ "content": "<|reserved_160|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "171": {
1358
+ "content": "<|reserved_161|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "172": {
1366
+ "content": "<|reserved_162|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "173": {
1374
+ "content": "<|reserved_163|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "174": {
1382
+ "content": "<|reserved_164|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "175": {
1390
+ "content": "<|reserved_165|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "176": {
1398
+ "content": "<|reserved_166|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "177": {
1406
+ "content": "<|reserved_167|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "178": {
1414
+ "content": "<|reserved_168|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "179": {
1422
+ "content": "<|reserved_169|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "180": {
1430
+ "content": "<|reserved_170|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "181": {
1438
+ "content": "<|reserved_171|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "182": {
1446
+ "content": "<|reserved_172|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "183": {
1454
+ "content": "<|reserved_173|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "184": {
1462
+ "content": "<|reserved_174|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "185": {
1470
+ "content": "<|reserved_175|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "186": {
1478
+ "content": "<|reserved_176|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "187": {
1486
+ "content": "<|reserved_177|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "188": {
1494
+ "content": "<|reserved_178|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "189": {
1502
+ "content": "<|reserved_179|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "190": {
1510
+ "content": "<|reserved_180|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "191": {
1518
+ "content": "<|reserved_181|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "192": {
1526
+ "content": "<|reserved_182|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "193": {
1534
+ "content": "<|reserved_183|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "194": {
1542
+ "content": "<|reserved_184|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "195": {
1550
+ "content": "<|reserved_185|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "196": {
1558
+ "content": "<|reserved_186|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "197": {
1566
+ "content": "<|reserved_187|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "198": {
1574
+ "content": "<|reserved_188|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "199": {
1582
+ "content": "<|reserved_189|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "200": {
1590
+ "content": "<|reserved_190|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "201": {
1598
+ "content": "<|reserved_191|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "202": {
1606
+ "content": "<|reserved_192|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "203": {
1614
+ "content": "<|reserved_193|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "204": {
1622
+ "content": "<|reserved_194|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "205": {
1630
+ "content": "<|reserved_195|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "206": {
1638
+ "content": "<|reserved_196|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "207": {
1646
+ "content": "<|reserved_197|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "208": {
1654
+ "content": "<|reserved_198|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "209": {
1662
+ "content": "<|reserved_199|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "210": {
1670
+ "content": "<|reserved_200|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "211": {
1678
+ "content": "<|reserved_201|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "212": {
1686
+ "content": "<|reserved_202|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "213": {
1694
+ "content": "<|reserved_203|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "214": {
1702
+ "content": "<|reserved_204|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "215": {
1710
+ "content": "<|reserved_205|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "216": {
1718
+ "content": "<|reserved_206|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "217": {
1726
+ "content": "<|reserved_207|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "218": {
1734
+ "content": "<|reserved_208|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "219": {
1742
+ "content": "<|reserved_209|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "220": {
1750
+ "content": "<|reserved_210|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "221": {
1758
+ "content": "<|reserved_211|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "222": {
1766
+ "content": "<|reserved_212|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "223": {
1774
+ "content": "<|reserved_213|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "224": {
1782
+ "content": "<|reserved_214|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "225": {
1790
+ "content": "<|reserved_215|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "226": {
1798
+ "content": "<|reserved_216|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "227": {
1806
+ "content": "<|reserved_217|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "228": {
1814
+ "content": "<|reserved_218|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "229": {
1822
+ "content": "<|reserved_219|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "230": {
1830
+ "content": "<|reserved_220|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "231": {
1838
+ "content": "<|reserved_221|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "232": {
1846
+ "content": "<|reserved_222|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "233": {
1854
+ "content": "<|reserved_223|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "234": {
1862
+ "content": "<|reserved_224|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "235": {
1870
+ "content": "<|reserved_225|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "236": {
1878
+ "content": "<|reserved_226|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "237": {
1886
+ "content": "<|reserved_227|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "238": {
1894
+ "content": "<|reserved_228|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "239": {
1902
+ "content": "<|reserved_229|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "240": {
1910
+ "content": "<|reserved_230|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "241": {
1918
+ "content": "<|reserved_231|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "242": {
1926
+ "content": "<|reserved_232|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "243": {
1934
+ "content": "<|reserved_233|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "244": {
1942
+ "content": "<|reserved_234|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "245": {
1950
+ "content": "<|reserved_235|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "246": {
1958
+ "content": "<|reserved_236|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "247": {
1966
+ "content": "<|reserved_237|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "248": {
1974
+ "content": "<|reserved_238|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "249": {
1982
+ "content": "<|reserved_239|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "250": {
1990
+ "content": "<|reserved_240|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "251": {
1998
+ "content": "<|reserved_241|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "252": {
2006
+ "content": "<|reserved_242|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "253": {
2014
+ "content": "<|reserved_243|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "254": {
2022
+ "content": "<|reserved_244|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "255": {
2030
+ "content": "<|reserved_245|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "256": {
2038
+ "content": "<|reserved_246|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "257": {
2046
+ "content": "<|reserved_247|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "258": {
2054
+ "content": "<|reserved_248|>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "259": {
2062
+ "content": "<|reserved_249|>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "260": {
2070
+ "content": "<|reserved_250|>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ },
2077
+ "261": {
2078
+ "content": "<|reserved_251|>",
2079
+ "lstrip": false,
2080
+ "normalized": false,
2081
+ "rstrip": false,
2082
+ "single_word": false,
2083
+ "special": true
2084
+ },
2085
+ "262": {
2086
+ "content": "<|reserved_252|>",
2087
+ "lstrip": false,
2088
+ "normalized": false,
2089
+ "rstrip": false,
2090
+ "single_word": false,
2091
+ "special": true
2092
+ },
2093
+ "263": {
2094
+ "content": "<|reserved_253|>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": true
2100
+ },
2101
+ "264": {
2102
+ "content": "<|reserved_254|>",
2103
+ "lstrip": false,
2104
+ "normalized": false,
2105
+ "rstrip": false,
2106
+ "single_word": false,
2107
+ "special": true
2108
+ },
2109
+ "265": {
2110
+ "content": "<|reserved_255|>",
2111
+ "lstrip": false,
2112
+ "normalized": false,
2113
+ "rstrip": false,
2114
+ "single_word": false,
2115
+ "special": true
2116
+ },
2117
+ "266": {
2118
+ "content": "<|reserved_256|>",
2119
+ "lstrip": false,
2120
+ "normalized": false,
2121
+ "rstrip": false,
2122
+ "single_word": false,
2123
+ "special": true
2124
+ },
2125
+ "267": {
2126
+ "content": "<|reserved_257|>",
2127
+ "lstrip": false,
2128
+ "normalized": false,
2129
+ "rstrip": false,
2130
+ "single_word": false,
2131
+ "special": true
2132
+ },
2133
+ "268": {
2134
+ "content": "<|reserved_258|>",
2135
+ "lstrip": false,
2136
+ "normalized": false,
2137
+ "rstrip": false,
2138
+ "single_word": false,
2139
+ "special": true
2140
+ },
2141
+ "269": {
2142
+ "content": "<|reserved_259|>",
2143
+ "lstrip": false,
2144
+ "normalized": false,
2145
+ "rstrip": false,
2146
+ "single_word": false,
2147
+ "special": true
2148
+ },
2149
+ "270": {
2150
+ "content": "<|reserved_260|>",
2151
+ "lstrip": false,
2152
+ "normalized": false,
2153
+ "rstrip": false,
2154
+ "single_word": false,
2155
+ "special": true
2156
+ },
2157
+ "271": {
2158
+ "content": "<|reserved_261|>",
2159
+ "lstrip": false,
2160
+ "normalized": false,
2161
+ "rstrip": false,
2162
+ "single_word": false,
2163
+ "special": true
2164
+ },
2165
+ "272": {
2166
+ "content": "<|reserved_262|>",
2167
+ "lstrip": false,
2168
+ "normalized": false,
2169
+ "rstrip": false,
2170
+ "single_word": false,
2171
+ "special": true
2172
+ },
2173
+ "273": {
2174
+ "content": "<|reserved_263|>",
2175
+ "lstrip": false,
2176
+ "normalized": false,
2177
+ "rstrip": false,
2178
+ "single_word": false,
2179
+ "special": true
2180
+ },
2181
+ "274": {
2182
+ "content": "<|reserved_264|>",
2183
+ "lstrip": false,
2184
+ "normalized": false,
2185
+ "rstrip": false,
2186
+ "single_word": false,
2187
+ "special": true
2188
+ },
2189
+ "275": {
2190
+ "content": "<|reserved_265|>",
2191
+ "lstrip": false,
2192
+ "normalized": false,
2193
+ "rstrip": false,
2194
+ "single_word": false,
2195
+ "special": true
2196
+ },
2197
+ "276": {
2198
+ "content": "<|reserved_266|>",
2199
+ "lstrip": false,
2200
+ "normalized": false,
2201
+ "rstrip": false,
2202
+ "single_word": false,
2203
+ "special": true
2204
+ },
2205
+ "277": {
2206
+ "content": "<|reserved_267|>",
2207
+ "lstrip": false,
2208
+ "normalized": false,
2209
+ "rstrip": false,
2210
+ "single_word": false,
2211
+ "special": true
2212
+ },
2213
+ "278": {
2214
+ "content": "<|reserved_268|>",
2215
+ "lstrip": false,
2216
+ "normalized": false,
2217
+ "rstrip": false,
2218
+ "single_word": false,
2219
+ "special": true
2220
+ },
2221
+ "279": {
2222
+ "content": "<|reserved_269|>",
2223
+ "lstrip": false,
2224
+ "normalized": false,
2225
+ "rstrip": false,
2226
+ "single_word": false,
2227
+ "special": true
2228
+ },
2229
+ "280": {
2230
+ "content": "<|reserved_270|>",
2231
+ "lstrip": false,
2232
+ "normalized": false,
2233
+ "rstrip": false,
2234
+ "single_word": false,
2235
+ "special": true
2236
+ },
2237
+ "281": {
2238
+ "content": "<|reserved_271|>",
2239
+ "lstrip": false,
2240
+ "normalized": false,
2241
+ "rstrip": false,
2242
+ "single_word": false,
2243
+ "special": true
2244
+ },
2245
+ "282": {
2246
+ "content": "<|reserved_272|>",
2247
+ "lstrip": false,
2248
+ "normalized": false,
2249
+ "rstrip": false,
2250
+ "single_word": false,
2251
+ "special": true
2252
+ },
2253
+ "283": {
2254
+ "content": "<|reserved_273|>",
2255
+ "lstrip": false,
2256
+ "normalized": false,
2257
+ "rstrip": false,
2258
+ "single_word": false,
2259
+ "special": true
2260
+ },
2261
+ "284": {
2262
+ "content": "<|reserved_274|>",
2263
+ "lstrip": false,
2264
+ "normalized": false,
2265
+ "rstrip": false,
2266
+ "single_word": false,
2267
+ "special": true
2268
+ },
2269
+ "285": {
2270
+ "content": "<|reserved_275|>",
2271
+ "lstrip": false,
2272
+ "normalized": false,
2273
+ "rstrip": false,
2274
+ "single_word": false,
2275
+ "special": true
2276
+ },
2277
+ "286": {
2278
+ "content": "<|reserved_276|>",
2279
+ "lstrip": false,
2280
+ "normalized": false,
2281
+ "rstrip": false,
2282
+ "single_word": false,
2283
+ "special": true
2284
+ },
2285
+ "287": {
2286
+ "content": "<|reserved_277|>",
2287
+ "lstrip": false,
2288
+ "normalized": false,
2289
+ "rstrip": false,
2290
+ "single_word": false,
2291
+ "special": true
2292
+ },
2293
+ "288": {
2294
+ "content": "<|reserved_278|>",
2295
+ "lstrip": false,
2296
+ "normalized": false,
2297
+ "rstrip": false,
2298
+ "single_word": false,
2299
+ "special": true
2300
+ },
2301
+ "289": {
2302
+ "content": "<|reserved_279|>",
2303
+ "lstrip": false,
2304
+ "normalized": false,
2305
+ "rstrip": false,
2306
+ "single_word": false,
2307
+ "special": true
2308
+ },
2309
+ "290": {
2310
+ "content": "<|reserved_280|>",
2311
+ "lstrip": false,
2312
+ "normalized": false,
2313
+ "rstrip": false,
2314
+ "single_word": false,
2315
+ "special": true
2316
+ },
2317
+ "291": {
2318
+ "content": "<|reserved_281|>",
2319
+ "lstrip": false,
2320
+ "normalized": false,
2321
+ "rstrip": false,
2322
+ "single_word": false,
2323
+ "special": true
2324
+ },
2325
+ "292": {
2326
+ "content": "<|reserved_282|>",
2327
+ "lstrip": false,
2328
+ "normalized": false,
2329
+ "rstrip": false,
2330
+ "single_word": false,
2331
+ "special": true
2332
+ },
2333
+ "293": {
2334
+ "content": "<|reserved_283|>",
2335
+ "lstrip": false,
2336
+ "normalized": false,
2337
+ "rstrip": false,
2338
+ "single_word": false,
2339
+ "special": true
2340
+ },
2341
+ "294": {
2342
+ "content": "<|reserved_284|>",
2343
+ "lstrip": false,
2344
+ "normalized": false,
2345
+ "rstrip": false,
2346
+ "single_word": false,
2347
+ "special": true
2348
+ },
2349
+ "295": {
2350
+ "content": "<|reserved_285|>",
2351
+ "lstrip": false,
2352
+ "normalized": false,
2353
+ "rstrip": false,
2354
+ "single_word": false,
2355
+ "special": true
2356
+ },
2357
+ "296": {
2358
+ "content": "<|reserved_286|>",
2359
+ "lstrip": false,
2360
+ "normalized": false,
2361
+ "rstrip": false,
2362
+ "single_word": false,
2363
+ "special": true
2364
+ },
2365
+ "297": {
2366
+ "content": "<|reserved_287|>",
2367
+ "lstrip": false,
2368
+ "normalized": false,
2369
+ "rstrip": false,
2370
+ "single_word": false,
2371
+ "special": true
2372
+ },
2373
+ "298": {
2374
+ "content": "<|reserved_288|>",
2375
+ "lstrip": false,
2376
+ "normalized": false,
2377
+ "rstrip": false,
2378
+ "single_word": false,
2379
+ "special": true
2380
+ },
2381
+ "299": {
2382
+ "content": "<|reserved_289|>",
2383
+ "lstrip": false,
2384
+ "normalized": false,
2385
+ "rstrip": false,
2386
+ "single_word": false,
2387
+ "special": true
2388
+ },
2389
+ "300": {
2390
+ "content": "<|reserved_290|>",
2391
+ "lstrip": false,
2392
+ "normalized": false,
2393
+ "rstrip": false,
2394
+ "single_word": false,
2395
+ "special": true
2396
+ },
2397
+ "301": {
2398
+ "content": "<|reserved_291|>",
2399
+ "lstrip": false,
2400
+ "normalized": false,
2401
+ "rstrip": false,
2402
+ "single_word": false,
2403
+ "special": true
2404
+ },
2405
+ "302": {
2406
+ "content": "<|reserved_292|>",
2407
+ "lstrip": false,
2408
+ "normalized": false,
2409
+ "rstrip": false,
2410
+ "single_word": false,
2411
+ "special": true
2412
+ },
2413
+ "303": {
2414
+ "content": "<|reserved_293|>",
2415
+ "lstrip": false,
2416
+ "normalized": false,
2417
+ "rstrip": false,
2418
+ "single_word": false,
2419
+ "special": true
2420
+ },
2421
+ "304": {
2422
+ "content": "<|reserved_294|>",
2423
+ "lstrip": false,
2424
+ "normalized": false,
2425
+ "rstrip": false,
2426
+ "single_word": false,
2427
+ "special": true
2428
+ },
2429
+ "305": {
2430
+ "content": "<|reserved_295|>",
2431
+ "lstrip": false,
2432
+ "normalized": false,
2433
+ "rstrip": false,
2434
+ "single_word": false,
2435
+ "special": true
2436
+ },
2437
+ "306": {
2438
+ "content": "<|reserved_296|>",
2439
+ "lstrip": false,
2440
+ "normalized": false,
2441
+ "rstrip": false,
2442
+ "single_word": false,
2443
+ "special": true
2444
+ },
2445
+ "307": {
2446
+ "content": "<|reserved_297|>",
2447
+ "lstrip": false,
2448
+ "normalized": false,
2449
+ "rstrip": false,
2450
+ "single_word": false,
2451
+ "special": true
2452
+ },
2453
+ "308": {
2454
+ "content": "<|reserved_298|>",
2455
+ "lstrip": false,
2456
+ "normalized": false,
2457
+ "rstrip": false,
2458
+ "single_word": false,
2459
+ "special": true
2460
+ },
2461
+ "309": {
2462
+ "content": "<|reserved_299|>",
2463
+ "lstrip": false,
2464
+ "normalized": false,
2465
+ "rstrip": false,
2466
+ "single_word": false,
2467
+ "special": true
2468
+ },
2469
+ "310": {
2470
+ "content": "<|reserved_300|>",
2471
+ "lstrip": false,
2472
+ "normalized": false,
2473
+ "rstrip": false,
2474
+ "single_word": false,
2475
+ "special": true
2476
+ },
2477
+ "311": {
2478
+ "content": "<|reserved_301|>",
2479
+ "lstrip": false,
2480
+ "normalized": false,
2481
+ "rstrip": false,
2482
+ "single_word": false,
2483
+ "special": true
2484
+ },
2485
+ "312": {
2486
+ "content": "<|reserved_302|>",
2487
+ "lstrip": false,
2488
+ "normalized": false,
2489
+ "rstrip": false,
2490
+ "single_word": false,
2491
+ "special": true
2492
+ },
2493
+ "313": {
2494
+ "content": "<|reserved_303|>",
2495
+ "lstrip": false,
2496
+ "normalized": false,
2497
+ "rstrip": false,
2498
+ "single_word": false,
2499
+ "special": true
2500
+ },
2501
+ "314": {
2502
+ "content": "<|reserved_304|>",
2503
+ "lstrip": false,
2504
+ "normalized": false,
2505
+ "rstrip": false,
2506
+ "single_word": false,
2507
+ "special": true
2508
+ },
2509
+ "315": {
2510
+ "content": "<|reserved_305|>",
2511
+ "lstrip": false,
2512
+ "normalized": false,
2513
+ "rstrip": false,
2514
+ "single_word": false,
2515
+ "special": true
2516
+ },
2517
+ "316": {
2518
+ "content": "<|reserved_306|>",
2519
+ "lstrip": false,
2520
+ "normalized": false,
2521
+ "rstrip": false,
2522
+ "single_word": false,
2523
+ "special": true
2524
+ },
2525
+ "317": {
2526
+ "content": "<|reserved_307|>",
2527
+ "lstrip": false,
2528
+ "normalized": false,
2529
+ "rstrip": false,
2530
+ "single_word": false,
2531
+ "special": true
2532
+ },
2533
+ "318": {
2534
+ "content": "<|reserved_308|>",
2535
+ "lstrip": false,
2536
+ "normalized": false,
2537
+ "rstrip": false,
2538
+ "single_word": false,
2539
+ "special": true
2540
+ },
2541
+ "319": {
2542
+ "content": "<|reserved_309|>",
2543
+ "lstrip": false,
2544
+ "normalized": false,
2545
+ "rstrip": false,
2546
+ "single_word": false,
2547
+ "special": true
2548
+ },
2549
+ "320": {
2550
+ "content": "<|reserved_310|>",
2551
+ "lstrip": false,
2552
+ "normalized": false,
2553
+ "rstrip": false,
2554
+ "single_word": false,
2555
+ "special": true
2556
+ },
2557
+ "321": {
2558
+ "content": "<|reserved_311|>",
2559
+ "lstrip": false,
2560
+ "normalized": false,
2561
+ "rstrip": false,
2562
+ "single_word": false,
2563
+ "special": true
2564
+ },
2565
+ "322": {
2566
+ "content": "<|reserved_312|>",
2567
+ "lstrip": false,
2568
+ "normalized": false,
2569
+ "rstrip": false,
2570
+ "single_word": false,
2571
+ "special": true
2572
+ },
2573
+ "323": {
2574
+ "content": "<|reserved_313|>",
2575
+ "lstrip": false,
2576
+ "normalized": false,
2577
+ "rstrip": false,
2578
+ "single_word": false,
2579
+ "special": true
2580
+ },
2581
+ "324": {
2582
+ "content": "<|reserved_314|>",
2583
+ "lstrip": false,
2584
+ "normalized": false,
2585
+ "rstrip": false,
2586
+ "single_word": false,
2587
+ "special": true
2588
+ },
2589
+ "325": {
2590
+ "content": "<|reserved_315|>",
2591
+ "lstrip": false,
2592
+ "normalized": false,
2593
+ "rstrip": false,
2594
+ "single_word": false,
2595
+ "special": true
2596
+ },
2597
+ "326": {
2598
+ "content": "<|reserved_316|>",
2599
+ "lstrip": false,
2600
+ "normalized": false,
2601
+ "rstrip": false,
2602
+ "single_word": false,
2603
+ "special": true
2604
+ },
2605
+ "327": {
2606
+ "content": "<|reserved_317|>",
2607
+ "lstrip": false,
2608
+ "normalized": false,
2609
+ "rstrip": false,
2610
+ "single_word": false,
2611
+ "special": true
2612
+ },
2613
+ "328": {
2614
+ "content": "<|reserved_318|>",
2615
+ "lstrip": false,
2616
+ "normalized": false,
2617
+ "rstrip": false,
2618
+ "single_word": false,
2619
+ "special": true
2620
+ },
2621
+ "329": {
2622
+ "content": "<|reserved_319|>",
2623
+ "lstrip": false,
2624
+ "normalized": false,
2625
+ "rstrip": false,
2626
+ "single_word": false,
2627
+ "special": true
2628
+ },
2629
+ "330": {
2630
+ "content": "<|reserved_320|>",
2631
+ "lstrip": false,
2632
+ "normalized": false,
2633
+ "rstrip": false,
2634
+ "single_word": false,
2635
+ "special": true
2636
+ },
2637
+ "331": {
2638
+ "content": "<|reserved_321|>",
2639
+ "lstrip": false,
2640
+ "normalized": false,
2641
+ "rstrip": false,
2642
+ "single_word": false,
2643
+ "special": true
2644
+ },
2645
+ "332": {
2646
+ "content": "<|reserved_322|>",
2647
+ "lstrip": false,
2648
+ "normalized": false,
2649
+ "rstrip": false,
2650
+ "single_word": false,
2651
+ "special": true
2652
+ },
2653
+ "333": {
2654
+ "content": "<|reserved_323|>",
2655
+ "lstrip": false,
2656
+ "normalized": false,
2657
+ "rstrip": false,
2658
+ "single_word": false,
2659
+ "special": true
2660
+ },
2661
+ "334": {
2662
+ "content": "<|reserved_324|>",
2663
+ "lstrip": false,
2664
+ "normalized": false,
2665
+ "rstrip": false,
2666
+ "single_word": false,
2667
+ "special": true
2668
+ },
2669
+ "335": {
2670
+ "content": "<|reserved_325|>",
2671
+ "lstrip": false,
2672
+ "normalized": false,
2673
+ "rstrip": false,
2674
+ "single_word": false,
2675
+ "special": true
2676
+ },
2677
+ "336": {
2678
+ "content": "<|reserved_326|>",
2679
+ "lstrip": false,
2680
+ "normalized": false,
2681
+ "rstrip": false,
2682
+ "single_word": false,
2683
+ "special": true
2684
+ },
2685
+ "337": {
2686
+ "content": "<|reserved_327|>",
2687
+ "lstrip": false,
2688
+ "normalized": false,
2689
+ "rstrip": false,
2690
+ "single_word": false,
2691
+ "special": true
2692
+ },
2693
+ "338": {
2694
+ "content": "<|reserved_328|>",
2695
+ "lstrip": false,
2696
+ "normalized": false,
2697
+ "rstrip": false,
2698
+ "single_word": false,
2699
+ "special": true
2700
+ },
2701
+ "339": {
2702
+ "content": "<|reserved_329|>",
2703
+ "lstrip": false,
2704
+ "normalized": false,
2705
+ "rstrip": false,
2706
+ "single_word": false,
2707
+ "special": true
2708
+ },
2709
+ "340": {
2710
+ "content": "<|reserved_330|>",
2711
+ "lstrip": false,
2712
+ "normalized": false,
2713
+ "rstrip": false,
2714
+ "single_word": false,
2715
+ "special": true
2716
+ },
2717
+ "341": {
2718
+ "content": "<|reserved_331|>",
2719
+ "lstrip": false,
2720
+ "normalized": false,
2721
+ "rstrip": false,
2722
+ "single_word": false,
2723
+ "special": true
2724
+ },
2725
+ "342": {
2726
+ "content": "<|reserved_332|>",
2727
+ "lstrip": false,
2728
+ "normalized": false,
2729
+ "rstrip": false,
2730
+ "single_word": false,
2731
+ "special": true
2732
+ },
2733
+ "343": {
2734
+ "content": "<|reserved_333|>",
2735
+ "lstrip": false,
2736
+ "normalized": false,
2737
+ "rstrip": false,
2738
+ "single_word": false,
2739
+ "special": true
2740
+ },
2741
+ "344": {
2742
+ "content": "<|reserved_334|>",
2743
+ "lstrip": false,
2744
+ "normalized": false,
2745
+ "rstrip": false,
2746
+ "single_word": false,
2747
+ "special": true
2748
+ },
2749
+ "345": {
2750
+ "content": "<|reserved_335|>",
2751
+ "lstrip": false,
2752
+ "normalized": false,
2753
+ "rstrip": false,
2754
+ "single_word": false,
2755
+ "special": true
2756
+ },
2757
+ "346": {
2758
+ "content": "<|reserved_336|>",
2759
+ "lstrip": false,
2760
+ "normalized": false,
2761
+ "rstrip": false,
2762
+ "single_word": false,
2763
+ "special": true
2764
+ },
2765
+ "347": {
2766
+ "content": "<|reserved_337|>",
2767
+ "lstrip": false,
2768
+ "normalized": false,
2769
+ "rstrip": false,
2770
+ "single_word": false,
2771
+ "special": true
2772
+ },
2773
+ "348": {
2774
+ "content": "<|reserved_338|>",
2775
+ "lstrip": false,
2776
+ "normalized": false,
2777
+ "rstrip": false,
2778
+ "single_word": false,
2779
+ "special": true
2780
+ },
2781
+ "349": {
2782
+ "content": "<|reserved_339|>",
2783
+ "lstrip": false,
2784
+ "normalized": false,
2785
+ "rstrip": false,
2786
+ "single_word": false,
2787
+ "special": true
2788
+ },
2789
+ "350": {
2790
+ "content": "<|reserved_340|>",
2791
+ "lstrip": false,
2792
+ "normalized": false,
2793
+ "rstrip": false,
2794
+ "single_word": false,
2795
+ "special": true
2796
+ },
2797
+ "351": {
2798
+ "content": "<|reserved_341|>",
2799
+ "lstrip": false,
2800
+ "normalized": false,
2801
+ "rstrip": false,
2802
+ "single_word": false,
2803
+ "special": true
2804
+ },
2805
+ "352": {
2806
+ "content": "<|reserved_342|>",
2807
+ "lstrip": false,
2808
+ "normalized": false,
2809
+ "rstrip": false,
2810
+ "single_word": false,
2811
+ "special": true
2812
+ },
2813
+ "353": {
2814
+ "content": "<|reserved_343|>",
2815
+ "lstrip": false,
2816
+ "normalized": false,
2817
+ "rstrip": false,
2818
+ "single_word": false,
2819
+ "special": true
2820
+ },
2821
+ "354": {
2822
+ "content": "<|reserved_344|>",
2823
+ "lstrip": false,
2824
+ "normalized": false,
2825
+ "rstrip": false,
2826
+ "single_word": false,
2827
+ "special": true
2828
+ },
2829
+ "355": {
2830
+ "content": "<|reserved_345|>",
2831
+ "lstrip": false,
2832
+ "normalized": false,
2833
+ "rstrip": false,
2834
+ "single_word": false,
2835
+ "special": true
2836
+ },
2837
+ "356": {
2838
+ "content": "<|reserved_346|>",
2839
+ "lstrip": false,
2840
+ "normalized": false,
2841
+ "rstrip": false,
2842
+ "single_word": false,
2843
+ "special": true
2844
+ },
2845
+ "357": {
2846
+ "content": "<|reserved_347|>",
2847
+ "lstrip": false,
2848
+ "normalized": false,
2849
+ "rstrip": false,
2850
+ "single_word": false,
2851
+ "special": true
2852
+ },
2853
+ "358": {
2854
+ "content": "<|reserved_348|>",
2855
+ "lstrip": false,
2856
+ "normalized": false,
2857
+ "rstrip": false,
2858
+ "single_word": false,
2859
+ "special": true
2860
+ },
2861
+ "359": {
2862
+ "content": "<|reserved_349|>",
2863
+ "lstrip": false,
2864
+ "normalized": false,
2865
+ "rstrip": false,
2866
+ "single_word": false,
2867
+ "special": true
2868
+ },
2869
+ "360": {
2870
+ "content": "<|reserved_350|>",
2871
+ "lstrip": false,
2872
+ "normalized": false,
2873
+ "rstrip": false,
2874
+ "single_word": false,
2875
+ "special": true
2876
+ },
2877
+ "361": {
2878
+ "content": "<|reserved_351|>",
2879
+ "lstrip": false,
2880
+ "normalized": false,
2881
+ "rstrip": false,
2882
+ "single_word": false,
2883
+ "special": true
2884
+ },
2885
+ "362": {
2886
+ "content": "<|reserved_352|>",
2887
+ "lstrip": false,
2888
+ "normalized": false,
2889
+ "rstrip": false,
2890
+ "single_word": false,
2891
+ "special": true
2892
+ },
2893
+ "363": {
2894
+ "content": "<|reserved_353|>",
2895
+ "lstrip": false,
2896
+ "normalized": false,
2897
+ "rstrip": false,
2898
+ "single_word": false,
2899
+ "special": true
2900
+ },
2901
+ "364": {
2902
+ "content": "<|reserved_354|>",
2903
+ "lstrip": false,
2904
+ "normalized": false,
2905
+ "rstrip": false,
2906
+ "single_word": false,
2907
+ "special": true
2908
+ },
2909
+ "365": {
2910
+ "content": "<|reserved_355|>",
2911
+ "lstrip": false,
2912
+ "normalized": false,
2913
+ "rstrip": false,
2914
+ "single_word": false,
2915
+ "special": true
2916
+ },
2917
+ "366": {
2918
+ "content": "<|reserved_356|>",
2919
+ "lstrip": false,
2920
+ "normalized": false,
2921
+ "rstrip": false,
2922
+ "single_word": false,
2923
+ "special": true
2924
+ },
2925
+ "367": {
2926
+ "content": "<|reserved_357|>",
2927
+ "lstrip": false,
2928
+ "normalized": false,
2929
+ "rstrip": false,
2930
+ "single_word": false,
2931
+ "special": true
2932
+ },
2933
+ "368": {
2934
+ "content": "<|reserved_358|>",
2935
+ "lstrip": false,
2936
+ "normalized": false,
2937
+ "rstrip": false,
2938
+ "single_word": false,
2939
+ "special": true
2940
+ },
2941
+ "369": {
2942
+ "content": "<|reserved_359|>",
2943
+ "lstrip": false,
2944
+ "normalized": false,
2945
+ "rstrip": false,
2946
+ "single_word": false,
2947
+ "special": true
2948
+ },
2949
+ "370": {
2950
+ "content": "<|reserved_360|>",
2951
+ "lstrip": false,
2952
+ "normalized": false,
2953
+ "rstrip": false,
2954
+ "single_word": false,
2955
+ "special": true
2956
+ },
2957
+ "371": {
2958
+ "content": "<|reserved_361|>",
2959
+ "lstrip": false,
2960
+ "normalized": false,
2961
+ "rstrip": false,
2962
+ "single_word": false,
2963
+ "special": true
2964
+ },
2965
+ "372": {
2966
+ "content": "<|reserved_362|>",
2967
+ "lstrip": false,
2968
+ "normalized": false,
2969
+ "rstrip": false,
2970
+ "single_word": false,
2971
+ "special": true
2972
+ },
2973
+ "373": {
2974
+ "content": "<|reserved_363|>",
2975
+ "lstrip": false,
2976
+ "normalized": false,
2977
+ "rstrip": false,
2978
+ "single_word": false,
2979
+ "special": true
2980
+ },
2981
+ "374": {
2982
+ "content": "<|reserved_364|>",
2983
+ "lstrip": false,
2984
+ "normalized": false,
2985
+ "rstrip": false,
2986
+ "single_word": false,
2987
+ "special": true
2988
+ },
2989
+ "375": {
2990
+ "content": "<|reserved_365|>",
2991
+ "lstrip": false,
2992
+ "normalized": false,
2993
+ "rstrip": false,
2994
+ "single_word": false,
2995
+ "special": true
2996
+ },
2997
+ "376": {
2998
+ "content": "<|reserved_366|>",
2999
+ "lstrip": false,
3000
+ "normalized": false,
3001
+ "rstrip": false,
3002
+ "single_word": false,
3003
+ "special": true
3004
+ },
3005
+ "377": {
3006
+ "content": "<|reserved_367|>",
3007
+ "lstrip": false,
3008
+ "normalized": false,
3009
+ "rstrip": false,
3010
+ "single_word": false,
3011
+ "special": true
3012
+ },
3013
+ "378": {
3014
+ "content": "<|reserved_368|>",
3015
+ "lstrip": false,
3016
+ "normalized": false,
3017
+ "rstrip": false,
3018
+ "single_word": false,
3019
+ "special": true
3020
+ },
3021
+ "379": {
3022
+ "content": "<|reserved_369|>",
3023
+ "lstrip": false,
3024
+ "normalized": false,
3025
+ "rstrip": false,
3026
+ "single_word": false,
3027
+ "special": true
3028
+ },
3029
+ "380": {
3030
+ "content": "<|reserved_370|>",
3031
+ "lstrip": false,
3032
+ "normalized": false,
3033
+ "rstrip": false,
3034
+ "single_word": false,
3035
+ "special": true
3036
+ },
3037
+ "381": {
3038
+ "content": "<|reserved_371|>",
3039
+ "lstrip": false,
3040
+ "normalized": false,
3041
+ "rstrip": false,
3042
+ "single_word": false,
3043
+ "special": true
3044
+ },
3045
+ "382": {
3046
+ "content": "<|reserved_372|>",
3047
+ "lstrip": false,
3048
+ "normalized": false,
3049
+ "rstrip": false,
3050
+ "single_word": false,
3051
+ "special": true
3052
+ },
3053
+ "383": {
3054
+ "content": "<|reserved_373|>",
3055
+ "lstrip": false,
3056
+ "normalized": false,
3057
+ "rstrip": false,
3058
+ "single_word": false,
3059
+ "special": true
3060
+ },
3061
+ "384": {
3062
+ "content": "<|reserved_374|>",
3063
+ "lstrip": false,
3064
+ "normalized": false,
3065
+ "rstrip": false,
3066
+ "single_word": false,
3067
+ "special": true
3068
+ },
3069
+ "385": {
3070
+ "content": "<|reserved_375|>",
3071
+ "lstrip": false,
3072
+ "normalized": false,
3073
+ "rstrip": false,
3074
+ "single_word": false,
3075
+ "special": true
3076
+ },
3077
+ "386": {
3078
+ "content": "<|reserved_376|>",
3079
+ "lstrip": false,
3080
+ "normalized": false,
3081
+ "rstrip": false,
3082
+ "single_word": false,
3083
+ "special": true
3084
+ },
3085
+ "387": {
3086
+ "content": "<|reserved_377|>",
3087
+ "lstrip": false,
3088
+ "normalized": false,
3089
+ "rstrip": false,
3090
+ "single_word": false,
3091
+ "special": true
3092
+ },
3093
+ "388": {
3094
+ "content": "<|reserved_378|>",
3095
+ "lstrip": false,
3096
+ "normalized": false,
3097
+ "rstrip": false,
3098
+ "single_word": false,
3099
+ "special": true
3100
+ },
3101
+ "389": {
3102
+ "content": "<|reserved_379|>",
3103
+ "lstrip": false,
3104
+ "normalized": false,
3105
+ "rstrip": false,
3106
+ "single_word": false,
3107
+ "special": true
3108
+ },
3109
+ "390": {
3110
+ "content": "<|reserved_380|>",
3111
+ "lstrip": false,
3112
+ "normalized": false,
3113
+ "rstrip": false,
3114
+ "single_word": false,
3115
+ "special": true
3116
+ },
3117
+ "391": {
3118
+ "content": "<|reserved_381|>",
3119
+ "lstrip": false,
3120
+ "normalized": false,
3121
+ "rstrip": false,
3122
+ "single_word": false,
3123
+ "special": true
3124
+ },
3125
+ "392": {
3126
+ "content": "<|reserved_382|>",
3127
+ "lstrip": false,
3128
+ "normalized": false,
3129
+ "rstrip": false,
3130
+ "single_word": false,
3131
+ "special": true
3132
+ },
3133
+ "393": {
3134
+ "content": "<|reserved_383|>",
3135
+ "lstrip": false,
3136
+ "normalized": false,
3137
+ "rstrip": false,
3138
+ "single_word": false,
3139
+ "special": true
3140
+ },
3141
+ "394": {
3142
+ "content": "<|reserved_384|>",
3143
+ "lstrip": false,
3144
+ "normalized": false,
3145
+ "rstrip": false,
3146
+ "single_word": false,
3147
+ "special": true
3148
+ },
3149
+ "395": {
3150
+ "content": "<|reserved_385|>",
3151
+ "lstrip": false,
3152
+ "normalized": false,
3153
+ "rstrip": false,
3154
+ "single_word": false,
3155
+ "special": true
3156
+ },
3157
+ "396": {
3158
+ "content": "<|reserved_386|>",
3159
+ "lstrip": false,
3160
+ "normalized": false,
3161
+ "rstrip": false,
3162
+ "single_word": false,
3163
+ "special": true
3164
+ },
3165
+ "397": {
3166
+ "content": "<|reserved_387|>",
3167
+ "lstrip": false,
3168
+ "normalized": false,
3169
+ "rstrip": false,
3170
+ "single_word": false,
3171
+ "special": true
3172
+ },
3173
+ "398": {
3174
+ "content": "<|reserved_388|>",
3175
+ "lstrip": false,
3176
+ "normalized": false,
3177
+ "rstrip": false,
3178
+ "single_word": false,
3179
+ "special": true
3180
+ },
3181
+ "399": {
3182
+ "content": "<|reserved_389|>",
3183
+ "lstrip": false,
3184
+ "normalized": false,
3185
+ "rstrip": false,
3186
+ "single_word": false,
3187
+ "special": true
3188
+ },
3189
+ "400": {
3190
+ "content": "<|reserved_390|>",
3191
+ "lstrip": false,
3192
+ "normalized": false,
3193
+ "rstrip": false,
3194
+ "single_word": false,
3195
+ "special": true
3196
+ },
3197
+ "401": {
3198
+ "content": "<|reserved_391|>",
3199
+ "lstrip": false,
3200
+ "normalized": false,
3201
+ "rstrip": false,
3202
+ "single_word": false,
3203
+ "special": true
3204
+ },
3205
+ "402": {
3206
+ "content": "<|reserved_392|>",
3207
+ "lstrip": false,
3208
+ "normalized": false,
3209
+ "rstrip": false,
3210
+ "single_word": false,
3211
+ "special": true
3212
+ },
3213
+ "403": {
3214
+ "content": "<|reserved_393|>",
3215
+ "lstrip": false,
3216
+ "normalized": false,
3217
+ "rstrip": false,
3218
+ "single_word": false,
3219
+ "special": true
3220
+ },
3221
+ "404": {
3222
+ "content": "<|reserved_394|>",
3223
+ "lstrip": false,
3224
+ "normalized": false,
3225
+ "rstrip": false,
3226
+ "single_word": false,
3227
+ "special": true
3228
+ },
3229
+ "405": {
3230
+ "content": "<|reserved_395|>",
3231
+ "lstrip": false,
3232
+ "normalized": false,
3233
+ "rstrip": false,
3234
+ "single_word": false,
3235
+ "special": true
3236
+ },
3237
+ "406": {
3238
+ "content": "<|reserved_396|>",
3239
+ "lstrip": false,
3240
+ "normalized": false,
3241
+ "rstrip": false,
3242
+ "single_word": false,
3243
+ "special": true
3244
+ },
3245
+ "407": {
3246
+ "content": "<|reserved_397|>",
3247
+ "lstrip": false,
3248
+ "normalized": false,
3249
+ "rstrip": false,
3250
+ "single_word": false,
3251
+ "special": true
3252
+ },
3253
+ "408": {
3254
+ "content": "<|reserved_398|>",
3255
+ "lstrip": false,
3256
+ "normalized": false,
3257
+ "rstrip": false,
3258
+ "single_word": false,
3259
+ "special": true
3260
+ },
3261
+ "409": {
3262
+ "content": "<|reserved_399|>",
3263
+ "lstrip": false,
3264
+ "normalized": false,
3265
+ "rstrip": false,
3266
+ "single_word": false,
3267
+ "special": true
3268
+ },
3269
+ "410": {
3270
+ "content": "<|reserved_400|>",
3271
+ "lstrip": false,
3272
+ "normalized": false,
3273
+ "rstrip": false,
3274
+ "single_word": false,
3275
+ "special": true
3276
+ },
3277
+ "411": {
3278
+ "content": "<|reserved_401|>",
3279
+ "lstrip": false,
3280
+ "normalized": false,
3281
+ "rstrip": false,
3282
+ "single_word": false,
3283
+ "special": true
3284
+ },
3285
+ "412": {
3286
+ "content": "<|reserved_402|>",
3287
+ "lstrip": false,
3288
+ "normalized": false,
3289
+ "rstrip": false,
3290
+ "single_word": false,
3291
+ "special": true
3292
+ },
3293
+ "413": {
3294
+ "content": "<|reserved_403|>",
3295
+ "lstrip": false,
3296
+ "normalized": false,
3297
+ "rstrip": false,
3298
+ "single_word": false,
3299
+ "special": true
3300
+ },
3301
+ "414": {
3302
+ "content": "<|reserved_404|>",
3303
+ "lstrip": false,
3304
+ "normalized": false,
3305
+ "rstrip": false,
3306
+ "single_word": false,
3307
+ "special": true
3308
+ },
3309
+ "415": {
3310
+ "content": "<|reserved_405|>",
3311
+ "lstrip": false,
3312
+ "normalized": false,
3313
+ "rstrip": false,
3314
+ "single_word": false,
3315
+ "special": true
3316
+ },
3317
+ "416": {
3318
+ "content": "<|reserved_406|>",
3319
+ "lstrip": false,
3320
+ "normalized": false,
3321
+ "rstrip": false,
3322
+ "single_word": false,
3323
+ "special": true
3324
+ },
3325
+ "417": {
3326
+ "content": "<|reserved_407|>",
3327
+ "lstrip": false,
3328
+ "normalized": false,
3329
+ "rstrip": false,
3330
+ "single_word": false,
3331
+ "special": true
3332
+ },
3333
+ "418": {
3334
+ "content": "<|reserved_408|>",
3335
+ "lstrip": false,
3336
+ "normalized": false,
3337
+ "rstrip": false,
3338
+ "single_word": false,
3339
+ "special": true
3340
+ },
3341
+ "419": {
3342
+ "content": "<|reserved_409|>",
3343
+ "lstrip": false,
3344
+ "normalized": false,
3345
+ "rstrip": false,
3346
+ "single_word": false,
3347
+ "special": true
3348
+ },
3349
+ "420": {
3350
+ "content": "<|reserved_410|>",
3351
+ "lstrip": false,
3352
+ "normalized": false,
3353
+ "rstrip": false,
3354
+ "single_word": false,
3355
+ "special": true
3356
+ },
3357
+ "421": {
3358
+ "content": "<|reserved_411|>",
3359
+ "lstrip": false,
3360
+ "normalized": false,
3361
+ "rstrip": false,
3362
+ "single_word": false,
3363
+ "special": true
3364
+ },
3365
+ "422": {
3366
+ "content": "<|reserved_412|>",
3367
+ "lstrip": false,
3368
+ "normalized": false,
3369
+ "rstrip": false,
3370
+ "single_word": false,
3371
+ "special": true
3372
+ },
3373
+ "423": {
3374
+ "content": "<|reserved_413|>",
3375
+ "lstrip": false,
3376
+ "normalized": false,
3377
+ "rstrip": false,
3378
+ "single_word": false,
3379
+ "special": true
3380
+ },
3381
+ "424": {
3382
+ "content": "<|reserved_414|>",
3383
+ "lstrip": false,
3384
+ "normalized": false,
3385
+ "rstrip": false,
3386
+ "single_word": false,
3387
+ "special": true
3388
+ },
3389
+ "425": {
3390
+ "content": "<|reserved_415|>",
3391
+ "lstrip": false,
3392
+ "normalized": false,
3393
+ "rstrip": false,
3394
+ "single_word": false,
3395
+ "special": true
3396
+ },
3397
+ "426": {
3398
+ "content": "<|reserved_416|>",
3399
+ "lstrip": false,
3400
+ "normalized": false,
3401
+ "rstrip": false,
3402
+ "single_word": false,
3403
+ "special": true
3404
+ },
3405
+ "427": {
3406
+ "content": "<|reserved_417|>",
3407
+ "lstrip": false,
3408
+ "normalized": false,
3409
+ "rstrip": false,
3410
+ "single_word": false,
3411
+ "special": true
3412
+ },
3413
+ "428": {
3414
+ "content": "<|reserved_418|>",
3415
+ "lstrip": false,
3416
+ "normalized": false,
3417
+ "rstrip": false,
3418
+ "single_word": false,
3419
+ "special": true
3420
+ },
3421
+ "429": {
3422
+ "content": "<|reserved_419|>",
3423
+ "lstrip": false,
3424
+ "normalized": false,
3425
+ "rstrip": false,
3426
+ "single_word": false,
3427
+ "special": true
3428
+ },
3429
+ "430": {
3430
+ "content": "<|reserved_420|>",
3431
+ "lstrip": false,
3432
+ "normalized": false,
3433
+ "rstrip": false,
3434
+ "single_word": false,
3435
+ "special": true
3436
+ },
3437
+ "431": {
3438
+ "content": "<|reserved_421|>",
3439
+ "lstrip": false,
3440
+ "normalized": false,
3441
+ "rstrip": false,
3442
+ "single_word": false,
3443
+ "special": true
3444
+ },
3445
+ "432": {
3446
+ "content": "<|reserved_422|>",
3447
+ "lstrip": false,
3448
+ "normalized": false,
3449
+ "rstrip": false,
3450
+ "single_word": false,
3451
+ "special": true
3452
+ },
3453
+ "433": {
3454
+ "content": "<|reserved_423|>",
3455
+ "lstrip": false,
3456
+ "normalized": false,
3457
+ "rstrip": false,
3458
+ "single_word": false,
3459
+ "special": true
3460
+ },
3461
+ "434": {
3462
+ "content": "<|reserved_424|>",
3463
+ "lstrip": false,
3464
+ "normalized": false,
3465
+ "rstrip": false,
3466
+ "single_word": false,
3467
+ "special": true
3468
+ },
3469
+ "435": {
3470
+ "content": "<|reserved_425|>",
3471
+ "lstrip": false,
3472
+ "normalized": false,
3473
+ "rstrip": false,
3474
+ "single_word": false,
3475
+ "special": true
3476
+ },
3477
+ "436": {
3478
+ "content": "<|reserved_426|>",
3479
+ "lstrip": false,
3480
+ "normalized": false,
3481
+ "rstrip": false,
3482
+ "single_word": false,
3483
+ "special": true
3484
+ },
3485
+ "437": {
3486
+ "content": "<|reserved_427|>",
3487
+ "lstrip": false,
3488
+ "normalized": false,
3489
+ "rstrip": false,
3490
+ "single_word": false,
3491
+ "special": true
3492
+ },
3493
+ "438": {
3494
+ "content": "<|reserved_428|>",
3495
+ "lstrip": false,
3496
+ "normalized": false,
3497
+ "rstrip": false,
3498
+ "single_word": false,
3499
+ "special": true
3500
+ },
3501
+ "439": {
3502
+ "content": "<|reserved_429|>",
3503
+ "lstrip": false,
3504
+ "normalized": false,
3505
+ "rstrip": false,
3506
+ "single_word": false,
3507
+ "special": true
3508
+ },
3509
+ "440": {
3510
+ "content": "<|reserved_430|>",
3511
+ "lstrip": false,
3512
+ "normalized": false,
3513
+ "rstrip": false,
3514
+ "single_word": false,
3515
+ "special": true
3516
+ },
3517
+ "441": {
3518
+ "content": "<|reserved_431|>",
3519
+ "lstrip": false,
3520
+ "normalized": false,
3521
+ "rstrip": false,
3522
+ "single_word": false,
3523
+ "special": true
3524
+ },
3525
+ "442": {
3526
+ "content": "<|reserved_432|>",
3527
+ "lstrip": false,
3528
+ "normalized": false,
3529
+ "rstrip": false,
3530
+ "single_word": false,
3531
+ "special": true
3532
+ },
3533
+ "443": {
3534
+ "content": "<|reserved_433|>",
3535
+ "lstrip": false,
3536
+ "normalized": false,
3537
+ "rstrip": false,
3538
+ "single_word": false,
3539
+ "special": true
3540
+ },
3541
+ "444": {
3542
+ "content": "<|reserved_434|>",
3543
+ "lstrip": false,
3544
+ "normalized": false,
3545
+ "rstrip": false,
3546
+ "single_word": false,
3547
+ "special": true
3548
+ },
3549
+ "445": {
3550
+ "content": "<|reserved_435|>",
3551
+ "lstrip": false,
3552
+ "normalized": false,
3553
+ "rstrip": false,
3554
+ "single_word": false,
3555
+ "special": true
3556
+ },
3557
+ "446": {
3558
+ "content": "<|reserved_436|>",
3559
+ "lstrip": false,
3560
+ "normalized": false,
3561
+ "rstrip": false,
3562
+ "single_word": false,
3563
+ "special": true
3564
+ },
3565
+ "447": {
3566
+ "content": "<|reserved_437|>",
3567
+ "lstrip": false,
3568
+ "normalized": false,
3569
+ "rstrip": false,
3570
+ "single_word": false,
3571
+ "special": true
3572
+ },
3573
+ "448": {
3574
+ "content": "<|reserved_438|>",
3575
+ "lstrip": false,
3576
+ "normalized": false,
3577
+ "rstrip": false,
3578
+ "single_word": false,
3579
+ "special": true
3580
+ },
3581
+ "449": {
3582
+ "content": "<|reserved_439|>",
3583
+ "lstrip": false,
3584
+ "normalized": false,
3585
+ "rstrip": false,
3586
+ "single_word": false,
3587
+ "special": true
3588
+ },
3589
+ "450": {
3590
+ "content": "<|reserved_440|>",
3591
+ "lstrip": false,
3592
+ "normalized": false,
3593
+ "rstrip": false,
3594
+ "single_word": false,
3595
+ "special": true
3596
+ },
3597
+ "451": {
3598
+ "content": "<|reserved_441|>",
3599
+ "lstrip": false,
3600
+ "normalized": false,
3601
+ "rstrip": false,
3602
+ "single_word": false,
3603
+ "special": true
3604
+ },
3605
+ "452": {
3606
+ "content": "<|reserved_442|>",
3607
+ "lstrip": false,
3608
+ "normalized": false,
3609
+ "rstrip": false,
3610
+ "single_word": false,
3611
+ "special": true
3612
+ },
3613
+ "453": {
3614
+ "content": "<|reserved_443|>",
3615
+ "lstrip": false,
3616
+ "normalized": false,
3617
+ "rstrip": false,
3618
+ "single_word": false,
3619
+ "special": true
3620
+ },
3621
+ "454": {
3622
+ "content": "<|reserved_444|>",
3623
+ "lstrip": false,
3624
+ "normalized": false,
3625
+ "rstrip": false,
3626
+ "single_word": false,
3627
+ "special": true
3628
+ },
3629
+ "455": {
3630
+ "content": "<|reserved_445|>",
3631
+ "lstrip": false,
3632
+ "normalized": false,
3633
+ "rstrip": false,
3634
+ "single_word": false,
3635
+ "special": true
3636
+ },
3637
+ "456": {
3638
+ "content": "<|reserved_446|>",
3639
+ "lstrip": false,
3640
+ "normalized": false,
3641
+ "rstrip": false,
3642
+ "single_word": false,
3643
+ "special": true
3644
+ },
3645
+ "457": {
3646
+ "content": "<|reserved_447|>",
3647
+ "lstrip": false,
3648
+ "normalized": false,
3649
+ "rstrip": false,
3650
+ "single_word": false,
3651
+ "special": true
3652
+ },
3653
+ "458": {
3654
+ "content": "<|reserved_448|>",
3655
+ "lstrip": false,
3656
+ "normalized": false,
3657
+ "rstrip": false,
3658
+ "single_word": false,
3659
+ "special": true
3660
+ },
3661
+ "459": {
3662
+ "content": "<|reserved_449|>",
3663
+ "lstrip": false,
3664
+ "normalized": false,
3665
+ "rstrip": false,
3666
+ "single_word": false,
3667
+ "special": true
3668
+ },
3669
+ "460": {
3670
+ "content": "<|reserved_450|>",
3671
+ "lstrip": false,
3672
+ "normalized": false,
3673
+ "rstrip": false,
3674
+ "single_word": false,
3675
+ "special": true
3676
+ },
3677
+ "461": {
3678
+ "content": "<|reserved_451|>",
3679
+ "lstrip": false,
3680
+ "normalized": false,
3681
+ "rstrip": false,
3682
+ "single_word": false,
3683
+ "special": true
3684
+ },
3685
+ "462": {
3686
+ "content": "<|reserved_452|>",
3687
+ "lstrip": false,
3688
+ "normalized": false,
3689
+ "rstrip": false,
3690
+ "single_word": false,
3691
+ "special": true
3692
+ },
3693
+ "463": {
3694
+ "content": "<|reserved_453|>",
3695
+ "lstrip": false,
3696
+ "normalized": false,
3697
+ "rstrip": false,
3698
+ "single_word": false,
3699
+ "special": true
3700
+ },
3701
+ "464": {
3702
+ "content": "<|reserved_454|>",
3703
+ "lstrip": false,
3704
+ "normalized": false,
3705
+ "rstrip": false,
3706
+ "single_word": false,
3707
+ "special": true
3708
+ },
3709
+ "465": {
3710
+ "content": "<|reserved_455|>",
3711
+ "lstrip": false,
3712
+ "normalized": false,
3713
+ "rstrip": false,
3714
+ "single_word": false,
3715
+ "special": true
3716
+ },
3717
+ "466": {
3718
+ "content": "<|reserved_456|>",
3719
+ "lstrip": false,
3720
+ "normalized": false,
3721
+ "rstrip": false,
3722
+ "single_word": false,
3723
+ "special": true
3724
+ },
3725
+ "467": {
3726
+ "content": "<|reserved_457|>",
3727
+ "lstrip": false,
3728
+ "normalized": false,
3729
+ "rstrip": false,
3730
+ "single_word": false,
3731
+ "special": true
3732
+ },
3733
+ "468": {
3734
+ "content": "<|reserved_458|>",
3735
+ "lstrip": false,
3736
+ "normalized": false,
3737
+ "rstrip": false,
3738
+ "single_word": false,
3739
+ "special": true
3740
+ },
3741
+ "469": {
3742
+ "content": "<|reserved_459|>",
3743
+ "lstrip": false,
3744
+ "normalized": false,
3745
+ "rstrip": false,
3746
+ "single_word": false,
3747
+ "special": true
3748
+ },
3749
+ "470": {
3750
+ "content": "<|reserved_460|>",
3751
+ "lstrip": false,
3752
+ "normalized": false,
3753
+ "rstrip": false,
3754
+ "single_word": false,
3755
+ "special": true
3756
+ },
3757
+ "471": {
3758
+ "content": "<|reserved_461|>",
3759
+ "lstrip": false,
3760
+ "normalized": false,
3761
+ "rstrip": false,
3762
+ "single_word": false,
3763
+ "special": true
3764
+ },
3765
+ "472": {
3766
+ "content": "<|reserved_462|>",
3767
+ "lstrip": false,
3768
+ "normalized": false,
3769
+ "rstrip": false,
3770
+ "single_word": false,
3771
+ "special": true
3772
+ },
3773
+ "473": {
3774
+ "content": "<|reserved_463|>",
3775
+ "lstrip": false,
3776
+ "normalized": false,
3777
+ "rstrip": false,
3778
+ "single_word": false,
3779
+ "special": true
3780
+ },
3781
+ "474": {
3782
+ "content": "<|reserved_464|>",
3783
+ "lstrip": false,
3784
+ "normalized": false,
3785
+ "rstrip": false,
3786
+ "single_word": false,
3787
+ "special": true
3788
+ },
3789
+ "475": {
3790
+ "content": "<|reserved_465|>",
3791
+ "lstrip": false,
3792
+ "normalized": false,
3793
+ "rstrip": false,
3794
+ "single_word": false,
3795
+ "special": true
3796
+ },
3797
+ "476": {
3798
+ "content": "<|reserved_466|>",
3799
+ "lstrip": false,
3800
+ "normalized": false,
3801
+ "rstrip": false,
3802
+ "single_word": false,
3803
+ "special": true
3804
+ },
3805
+ "477": {
3806
+ "content": "<|reserved_467|>",
3807
+ "lstrip": false,
3808
+ "normalized": false,
3809
+ "rstrip": false,
3810
+ "single_word": false,
3811
+ "special": true
3812
+ },
3813
+ "478": {
3814
+ "content": "<|reserved_468|>",
3815
+ "lstrip": false,
3816
+ "normalized": false,
3817
+ "rstrip": false,
3818
+ "single_word": false,
3819
+ "special": true
3820
+ },
3821
+ "479": {
3822
+ "content": "<|reserved_469|>",
3823
+ "lstrip": false,
3824
+ "normalized": false,
3825
+ "rstrip": false,
3826
+ "single_word": false,
3827
+ "special": true
3828
+ },
3829
+ "480": {
3830
+ "content": "<|reserved_470|>",
3831
+ "lstrip": false,
3832
+ "normalized": false,
3833
+ "rstrip": false,
3834
+ "single_word": false,
3835
+ "special": true
3836
+ },
3837
+ "481": {
3838
+ "content": "<|reserved_471|>",
3839
+ "lstrip": false,
3840
+ "normalized": false,
3841
+ "rstrip": false,
3842
+ "single_word": false,
3843
+ "special": true
3844
+ },
3845
+ "482": {
3846
+ "content": "<|reserved_472|>",
3847
+ "lstrip": false,
3848
+ "normalized": false,
3849
+ "rstrip": false,
3850
+ "single_word": false,
3851
+ "special": true
3852
+ },
3853
+ "483": {
3854
+ "content": "<|reserved_473|>",
3855
+ "lstrip": false,
3856
+ "normalized": false,
3857
+ "rstrip": false,
3858
+ "single_word": false,
3859
+ "special": true
3860
+ },
3861
+ "484": {
3862
+ "content": "<|reserved_474|>",
3863
+ "lstrip": false,
3864
+ "normalized": false,
3865
+ "rstrip": false,
3866
+ "single_word": false,
3867
+ "special": true
3868
+ },
3869
+ "485": {
3870
+ "content": "<|reserved_475|>",
3871
+ "lstrip": false,
3872
+ "normalized": false,
3873
+ "rstrip": false,
3874
+ "single_word": false,
3875
+ "special": true
3876
+ },
3877
+ "486": {
3878
+ "content": "<|reserved_476|>",
3879
+ "lstrip": false,
3880
+ "normalized": false,
3881
+ "rstrip": false,
3882
+ "single_word": false,
3883
+ "special": true
3884
+ },
3885
+ "487": {
3886
+ "content": "<|reserved_477|>",
3887
+ "lstrip": false,
3888
+ "normalized": false,
3889
+ "rstrip": false,
3890
+ "single_word": false,
3891
+ "special": true
3892
+ },
3893
+ "488": {
3894
+ "content": "<|reserved_478|>",
3895
+ "lstrip": false,
3896
+ "normalized": false,
3897
+ "rstrip": false,
3898
+ "single_word": false,
3899
+ "special": true
3900
+ },
3901
+ "489": {
3902
+ "content": "<|reserved_479|>",
3903
+ "lstrip": false,
3904
+ "normalized": false,
3905
+ "rstrip": false,
3906
+ "single_word": false,
3907
+ "special": true
3908
+ },
3909
+ "490": {
3910
+ "content": "<|reserved_480|>",
3911
+ "lstrip": false,
3912
+ "normalized": false,
3913
+ "rstrip": false,
3914
+ "single_word": false,
3915
+ "special": true
3916
+ },
3917
+ "491": {
3918
+ "content": "<|reserved_481|>",
3919
+ "lstrip": false,
3920
+ "normalized": false,
3921
+ "rstrip": false,
3922
+ "single_word": false,
3923
+ "special": true
3924
+ },
3925
+ "492": {
3926
+ "content": "<|reserved_482|>",
3927
+ "lstrip": false,
3928
+ "normalized": false,
3929
+ "rstrip": false,
3930
+ "single_word": false,
3931
+ "special": true
3932
+ },
3933
+ "493": {
3934
+ "content": "<|reserved_483|>",
3935
+ "lstrip": false,
3936
+ "normalized": false,
3937
+ "rstrip": false,
3938
+ "single_word": false,
3939
+ "special": true
3940
+ },
3941
+ "494": {
3942
+ "content": "<|reserved_484|>",
3943
+ "lstrip": false,
3944
+ "normalized": false,
3945
+ "rstrip": false,
3946
+ "single_word": false,
3947
+ "special": true
3948
+ },
3949
+ "495": {
3950
+ "content": "<|reserved_485|>",
3951
+ "lstrip": false,
3952
+ "normalized": false,
3953
+ "rstrip": false,
3954
+ "single_word": false,
3955
+ "special": true
3956
+ },
3957
+ "496": {
3958
+ "content": "<|reserved_486|>",
3959
+ "lstrip": false,
3960
+ "normalized": false,
3961
+ "rstrip": false,
3962
+ "single_word": false,
3963
+ "special": true
3964
+ },
3965
+ "497": {
3966
+ "content": "<|reserved_487|>",
3967
+ "lstrip": false,
3968
+ "normalized": false,
3969
+ "rstrip": false,
3970
+ "single_word": false,
3971
+ "special": true
3972
+ },
3973
+ "498": {
3974
+ "content": "<|reserved_488|>",
3975
+ "lstrip": false,
3976
+ "normalized": false,
3977
+ "rstrip": false,
3978
+ "single_word": false,
3979
+ "special": true
3980
+ },
3981
+ "499": {
3982
+ "content": "<|reserved_489|>",
3983
+ "lstrip": false,
3984
+ "normalized": false,
3985
+ "rstrip": false,
3986
+ "single_word": false,
3987
+ "special": true
3988
+ },
3989
+ "500": {
3990
+ "content": "<|reserved_490|>",
3991
+ "lstrip": false,
3992
+ "normalized": false,
3993
+ "rstrip": false,
3994
+ "single_word": false,
3995
+ "special": true
3996
+ },
3997
+ "64011": {
3998
+ "content": "Mathias",
3999
+ "lstrip": false,
4000
+ "normalized": true,
4001
+ "rstrip": false,
4002
+ "single_word": false,
4003
+ "special": false
4004
+ },
4005
+ "64014": {
4006
+ "content": "python",
4007
+ "lstrip": false,
4008
+ "normalized": true,
4009
+ "rstrip": false,
4010
+ "single_word": false,
4011
+ "special": false
4012
+ },
4013
+ "64394": {
4014
+ "content": "<|cot_start|>",
4015
+ "lstrip": false,
4016
+ "normalized": false,
4017
+ "rstrip": false,
4018
+ "single_word": false,
4019
+ "special": true
4020
+ },
4021
+ "64395": {
4022
+ "content": "<|cot_end|>",
4023
+ "lstrip": false,
4024
+ "normalized": false,
4025
+ "rstrip": false,
4026
+ "single_word": false,
4027
+ "special": true
4028
+ },
4029
+ "64396": {
4030
+ "content": "<|review_start|>",
4031
+ "lstrip": false,
4032
+ "normalized": false,
4033
+ "rstrip": false,
4034
+ "single_word": false,
4035
+ "special": true
4036
+ },
4037
+ "64397": {
4038
+ "content": "<|review_end|>",
4039
+ "lstrip": false,
4040
+ "normalized": false,
4041
+ "rstrip": false,
4042
+ "single_word": false,
4043
+ "special": true
4044
+ },
4045
+ "64398": {
4046
+ "content": "<|file_start|>",
4047
+ "lstrip": false,
4048
+ "normalized": false,
4049
+ "rstrip": false,
4050
+ "single_word": false,
4051
+ "special": true
4052
+ },
4053
+ "64399": {
4054
+ "content": "<|file_end|>",
4055
+ "lstrip": false,
4056
+ "normalized": false,
4057
+ "rstrip": false,
4058
+ "single_word": false,
4059
+ "special": true
4060
+ }
4061
+ },
4062
+ "bos_token": "<|startoftext|>",
4063
+ "clean_up_tokenization_spaces": true,
4064
+ "eos_token": "<|im_end|>",
4065
+ "extra_special_tokens": {},
4066
+ "legacy": false,
4067
+ "model_input_names": [
4068
+ "input_ids",
4069
+ "attention_mask"
4070
+ ],
4071
+ "model_max_length": 8192,
4072
+ "pad_token": "<|pad|>",
4073
+ "padding_side": "right",
4074
+ "sp_model_kwargs": {},
4075
+ "spaces_between_special_tokens": false,
4076
+ "tokenizer_class": "PreTrainedTokenizerFast",
4077
+ "use_default_system_prompt": false,
4078
+ "use_fast": true
4079
+ }
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae74a063dfe600c6f32b1bc95d1859eed6da1102aff5c3bd36433e1a52f644e
3
+ size 22450639
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac176e86b0f24fa99a9ea94ab63d423fda16a3edec685d6bc88d424a4fda96e0
3
+ size 8081
zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info("Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info("Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)