Hugging Face's logo

TroyDoesAI
/
BlackSheep-RP-3xMoE

PyTorch
Safetensors
mixtral
Model card Files Community
TroyDoesAI commited on
Commit
f5f5f5c
•
1 Parent(s): f3b8374

Half Epoch checkpoint:

Browse files

11:27:54-941537 INFO Loading JSON datasets
Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1365/1365 [00:05<00:00, 262.82 examples/s]
11:28:00-429977 INFO Getting model ready
11:28:00-437996 INFO Preparing for training
11:28:00-439851 INFO Creating LoRA model
11:28:00-893558 INFO Starting training
Training 'mixtral' model using (q, v) projections
Trainable params: 50,331,648 (1.1246 %), All params: 4,475,538,432 (Model: 4,425,206,784)
11:28:01-555106 INFO Log file 'train_dataset_sample.json' created in the 'logs' directory.
Step: 4 {'loss': 0.0668, 'grad_norm': 0.1359836459159851, 'learning_rate': 9.963736263736264e-06, 'epoch': 0.003663003663003663}
Step: 9 {'loss': 0.0916, 'grad_norm': 0.2279471606016159, 'learning_rate': 9.927472527472529e-06, 'epoch': 0.007326007326007326}
Step: 14 {'loss': 0.0753, 'grad_norm': 0.4511280357837677, 'learning_rate': 9.891208791208792e-06, 'epoch': 0.01098901098901099}
Step: 19 {'loss': 0.084, 'grad_norm': 0.24976688623428345, 'learning_rate': 9.854945054945056e-06, 'epoch': 0.014652014652014652}
Step: 24 {'loss': 0.0741, 'grad_norm': 0.09527433663606644, 'learning_rate': 9.81868131868132e-06, 'epoch': 0.018315018315018316}
Step: 29 {'loss': 0.076, 'grad_norm': 0.06122274696826935, 'learning_rate': 9.782417582417582e-06, 'epoch': 0.02197802197802198}
Step: 34 {'loss': 0.082, 'grad_norm': 0.26327070593833923, 'learning_rate': 9.746153846153847e-06, 'epoch': 0.02564102564102564}
Step: 39 {'loss': 0.0612, 'grad_norm': 0.2465166449546814, 'learning_rate': 9.70989010989011e-06, 'epoch': 0.029304029304029304}
Step: 44 {'loss': 0.0733, 'grad_norm': 0.08420123159885406, 'learning_rate': 9.673626373626375e-06, 'epoch': 0.03296703296703297}
Step: 49 {'loss': 0.0565, 'grad_norm': 0.25095030665397644, 'learning_rate': 9.637362637362638e-06, 'epoch': 0.03663003663003663}
Step: 54 {'loss': 0.0902, 'grad_norm': 0.33763477206230164, 'learning_rate': 9.601098901098903e-06, 'epoch': 0.040293040293040296}
Step: 59 {'loss': 0.1316, 'grad_norm': 0.5101003050804138, 'learning_rate': 9.564835164835166e-06, 'epoch': 0.04395604395604396}
Step: 64 {'loss': 0.1362, 'grad_norm': 0.45701834559440613, 'learning_rate': 9.528571428571429e-06, 'epoch': 0.047619047619047616}
Step: 69 {'loss': 0.1631, 'grad_norm': 0.563866376876831, 'learning_rate': 9.492307692307693e-06, 'epoch': 0.05128205128205128}
Step: 74 {'loss': 0.1354, 'grad_norm': 0.10952164232730865, 'learning_rate': 9.456043956043956e-06, 'epoch': 0.054945054945054944}
Step: 79 {'loss': 0.1858, 'grad_norm': 0.22133922576904297, 'learning_rate': 9.419780219780221e-06, 'epoch': 0.05860805860805861}
Step: 84 {'loss': 0.1611, 'grad_norm': 0.521860659122467, 'learning_rate': 9.383516483516484e-06, 'epoch': 0.06227106227106227}
Step: 89 {'loss': 0.1508, 'grad_norm': 0.56801837682724, 'learning_rate': 9.347252747252749e-06, 'epoch': 0.06593406593406594}
Step: 94 {'loss': 0.1257, 'grad_norm': 0.5347073674201965, 'learning_rate': 9.310989010989012e-06, 'epoch': 0.0695970695970696}
Step: 99 {'loss': 0.187, 'grad_norm': 0.5496135950088501, 'learning_rate': 9.274725274725277e-06, 'epoch': 0.07326007326007326}
Step: 104 {'loss': 0.1954, 'grad_norm': 0.7482754588127136, 'learning_rate': 9.23846153846154e-06, 'epoch': 0.07692307692307693}
Step: 109 {'loss': 0.1157, 'grad_norm': 0.11614499986171722, 'learning_rate': 9.202197802197803e-06, 'epoch': 0.08058608058608059}
Step: 114 {'loss': 0.1099, 'grad_norm': 0.21353064477443695, 'learning_rate': 9.165934065934066e-06, 'epoch': 0.08424908424908426}
Step: 119 {'loss': 0.1752, 'grad_norm': 0.4894441068172455, 'learning_rate': 9.12967032967033e-06, 'epoch': 0.08791208791208792}
Step: 124 {'loss': 0.1616, 'grad_norm': 0.6079414486885071, 'learning_rate': 9.093406593406593e-06, 'epoch': 0.09157509157509157}
Step: 129 {'loss': 0.1349, 'grad_norm': 0.08628781884908676, 'learning_rate': 9.057142857142858e-06, 'epoch': 0.09523809523809523}
Step: 134 {'loss': 0.1627, 'grad_norm': 0.5504783987998962, 'learning_rate': 9.020879120879121e-06, 'epoch': 0.0989010989010989}
Step: 139 {'loss': 0.1627, 'grad_norm': 1.0104156732559204, 'learning_rate': 8.984615384615386e-06, 'epoch': 0.10256410256410256}
Step: 144 {'loss': 0.111, 'grad_norm': 0.2242872714996338, 'learning_rate': 8.948351648351649e-06, 'epoch': 0.10622710622710622}
Step: 149 {'loss': 0.1287, 'grad_norm': 0.20702646672725677, 'learning_rate': 8.912087912087912e-06, 'epoch': 0.10989010989010989}
Step: 154 {'loss': 0.1564, 'grad_norm': 0.42282870411872864, 'learning_rate': 8.875824175824177e-06, 'epoch': 0.11355311355311355}
Step: 159 {'loss': 0.1234, 'grad_norm': 0.29965367913246155, 'learning_rate': 8.83956043956044e-06, 'epoch': 0.11721611721611722}
Step: 164 {'loss': 0.1386, 'grad_norm': 0.25579577684402466, 'learning_rate': 8.803296703296704e-06, 'epoch': 0.12087912087912088}
Step: 169 {'loss': 0.1429, 'grad_norm': 0.9871158599853516, 'learning_rate': 8.767032967032967e-06, 'epoch': 0.12454212454212454}
Step: 174 {'loss': 0.1491, 'grad_norm': 0.4206677973270416, 'learning_rate': 8.730769230769232e-06, 'epoch': 0.1282051282051282}
Step: 179 {'loss': 0.1145, 'grad_norm': 0.5669340491294861, 'learning_rate': 8.694505494505495e-06, 'epoch': 0.13186813186813187}
Step: 184 {'loss': 0.123, 'grad_norm': 0.1574435532093048, 'learning_rate': 8.65824175824176e-06, 'epoch': 0.13553113553113552}
Step: 189 {'loss': 0.1693, 'grad_norm': 0.5592064261436462, 'learning_rate': 8.621978021978023e-06, 'epoch': 0.1391941391941392}
Step: 194 {'loss': 0.1243, 'grad_norm': 0.5779590606689453, 'learning_rate': 8.585714285714287e-06, 'epoch': 0.14285714285714285}
Step: 199 {'loss': 0.1396, 'grad_norm': 0.11793188750743866, 'learning_rate': 8.54945054945055e-06, 'epoch': 0.14652014652014653}
Step: 204 {'loss': 0.1117, 'grad_norm': 0.5391713976860046, 'learning_rate': 8.513186813186814e-06, 'epoch': 0.15018315018315018}
Step: 209 {'loss': 0.1466, 'grad_norm': 0.921928882598877, 'learning_rate': 8.476923076923078e-06, 'epoch': 0.15384615384615385}
Step: 214 {'loss': 0.1295, 'grad_norm': 0.48140949010849, 'learning_rate': 8.440659340659341e-06, 'epoch': 0.1575091575091575}
Step: 219 {'loss': 0.1887, 'grad_norm': 0.658561646938324, 'learning_rate': 8.404395604395606e-06, 'epoch': 0.16117216117216118}
Step: 224 {'loss': 0.1308, 'grad_norm': 0.6024790406227112, 'learning_rate': 8.368131868131869e-06, 'epoch': 0.16483516483516483}
Step: 229 {'loss': 0.067, 'grad_norm': 0.24153736233711243, 'learning_rate': 8.331868131868132e-06, 'epoch': 0.1684981684981685}
Step: 234 {'loss': 0.117, 'grad_norm': 0.17423799633979797, 'learning_rate': 8.295604395604395e-06, 'epoch': 0.17216117216117216}
Step: 239 {'loss': 0.1445, 'grad_norm': 0.6188604831695557, 'learning_rate': 8.25934065934066e-06, 'epoch': 0.17582417582417584}
Step: 244 {'loss': 0.1086, 'grad_norm': 0.47320955991744995, 'learning_rate': 8.223076923076923e-06, 'epoch': 0.1794871794871795}
Step: 249 {'loss': 0.1047, 'grad_norm': 0.22519785165786743, 'learning_rate': 8.186813186813188e-06, 'epoch': 0.18315018315018314}
Step: 254 {'loss': 0.1507, 'grad_norm': 0.8073124885559082, 'learning_rate': 8.15054945054945e-06, 'epoch': 0.18681318681318682}
Step: 259 {'loss': 0.1354, 'grad_norm': 0.5822990536689758, 'learning_rate': 8.114285714285715e-06, 'epoch': 0.19047619047619047}
Step: 264 {'loss': 0.1733, 'grad_norm': 0.7305815815925598, 'learning_rate': 8.078021978021978e-06, 'epoch': 0.19413919413919414}
Step: 269 {'loss': 0.1101, 'grad_norm': 0.4647897779941559, 'learning_rate': 8.041758241758243e-06, 'epoch': 0.1978021978021978}
Step: 274 {'loss': 0.1054, 'grad_norm': 0.6543989181518555, 'learning_rate': 8.005494505494506e-06, 'epoch': 0.20146520146520147}
Step: 279 {'loss': 0.1129, 'grad_norm': 0.8039067983627319, 'learning_rate': 7.96923076923077e-06, 'epoch': 0.20512820512820512}
Step: 284 {'loss': 0.1249, 'grad_norm': 0.35283106565475464, 'learning_rate': 7.932967032967034e-06, 'epoch': 0.2087912087912088}
Step: 289 {'loss': 0.1549, 'grad_norm': 0.6537496447563171, 'learning_rate': 7.896703296703297e-06, 'epoch': 0.21245421245421245}
Step: 294 {'loss': 0.0883, 'grad_norm': 0.23383976519107819, 'learning_rate': 7.860439560439561e-06, 'epoch': 0.21611721611721613}
Step: 299 {'loss': 0.1313, 'grad_norm': 0.1237742155790329, 'learning_rate': 7.824175824175825e-06, 'epoch': 0.21978021978021978}
Step: 304 {'loss': 0.1591, 'grad_norm': 0.7631969451904297, 'learning_rate': 7.78791208791209e-06, 'epoch': 0.22344322344322345}
Step: 309 {'loss': 0.0925, 'grad_norm': 0.48745134472846985, 'learning_rate': 7.751648351648352e-06, 'epoch': 0.2271062271062271}
Step: 314 {'loss': 0.1326, 'grad_norm': 0.6884176731109619, 'learning_rate': 7.715384615384615e-06, 'epoch': 0.23076923076923078}
Step: 319 {'loss': 0.125, 'grad_norm': 0.41068509221076965, 'learning_rate': 7.679120879120878e-06, 'epoch': 0.23443223443223443}
Step: 324 {'loss': 0.1141, 'grad_norm': 1.1253948211669922, 'learning_rate': 7.642857142857143e-06, 'epoch': 0.23809523809523808}
Step: 329 {'loss': 0.1702, 'grad_norm': 0.7410513162612915, 'learning_rate': 7.606593406593405e-06, 'epoch': 0.24175824175824176}
Step: 334 {'loss': 0.1521, 'grad_norm': 0.9737598896026611, 'learning_rate': 7.57032967032967e-06, 'epoch': 0.2454212454212454}
Step: 339 {'loss': 0.137, 'grad_norm': 1.0085108280181885, 'learning_rate': 7.534065934065934e-06, 'epoch': 0.2490842490842491}
Step: 344 {'loss': 0.0966, 'grad_norm': 0.486762672662735, 'learning_rate': 7.497802197802198e-06, 'epoch': 0.25274725274725274}
Step: 349 {'loss': 0.1231, 'grad_norm': 0.801877498626709, 'learning_rate': 7.4615384615384615e-06, 'epoch': 0.2564102564102564}
Step: 354 {'loss': 0.1453, 'grad_norm': 0.6585664749145508, 'learning_rate': 7.425274725274726e-06, 'epoch': 0.2600732600732601}
Step: 359 {'loss': 0.1296, 'grad_norm': 0.2636565566062927, 'learning_rate': 7.389010989010989e-06, 'epoch': 0.26373626373626374}
Step: 364 {'loss': 0.0983, 'grad_norm': 0.25512686371803284, 'learning_rat

Files changed (13) hide show
  1. added_tokens.json +40 -0
  2. config.json +35 -0
  3. generation_config.json +6 -0
  4. mergekit_moe_config.yml +144 -0
  5. pytorch_model-00001-of-00004.bin +3 -0
  6. pytorch_model-00002-of-00004.bin +3 -0
  7. pytorch_model-00003-of-00004.bin +3 -0
  8. pytorch_model-00004-of-00004.bin +3 -0
  9. pytorch_model.bin.index.json +522 -0
  10. special_tokens_map.json +33 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +350 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".\\DigitalSoul",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 16384,
15
+ "mlp_bias": false,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 3,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "num_local_experts": 3,
22
+ "output_router_logits": false,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "router_jitter_noise": 0.0,
29
+ "sliding_window": null,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.44.0",
33
+ "use_cache": true,
34
+ "vocab_size": 32064
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.44.0"
6
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: TroyDoesAI/BlackSheep-4B
2
+ gate_mode: random # one of "hidden", "cheap_embed", or "random"
3
+
4
+ # There are three methods for populating the MoE gates implemented.
5
+
6
+ # "hidden"
7
+ # Uses the hidden state representations of the positive/negative prompts for MoE gate parameters. Best quality and most effective option; the default. Requires evaluating each prompt using the base model so you might not be able to use this on constrained hardware (depending on the model). You can use --load-in-8bit or --load-in-4bit to reduce VRAM usage.
8
+
9
+ # "cheap_embed"
10
+ # Uses only the raw token embedding of the prompts, using the same gate parameters for every layer. Distinctly less effective than "hidden". Can be run on much, much lower end hardware.
11
+
12
+ # "random"
13
+ # Randomly initializes the MoE gates. Good for if you are going to fine tune the model afterwards, or maybe if you want something a little unhinged? I won't judge.
14
+
15
+ experts:
16
+ - source_model: TroyDoesAI/BlackSheep-4B
17
+ positive_prompts:
18
+ - "digital"
19
+ - "soul"
20
+ - "<|assistant|>"
21
+ - "instruction"
22
+ - "input"
23
+ - "output"
24
+ - "response"
25
+ - "story"
26
+ - "stories"
27
+ - "creative"
28
+ - "curious"
29
+ - "action"
30
+ - "sensitive"
31
+ - "pleasant"
32
+ - "thoughtful"
33
+ - "interesting"
34
+ - "BEGININPUT"
35
+ - "BEGINCONTEXT"
36
+ - "ENDCONTEXT"
37
+ - "ENDINPUT"
38
+ - "BEGININSTRUCTION"
39
+ - "ENDINSTRUCTION"
40
+ - "url"
41
+ - "date"
42
+ - "source"
43
+ - "context"
44
+ - "cite"
45
+ - "mermaid"
46
+ - "flow"
47
+ - "diagram"
48
+ - "sequence"
49
+ - "series"
50
+ - "code to flow"
51
+ - "code to diagram"
52
+ - "python to flow diagram"
53
+ - "program to flow"
54
+ - "program to flow diagram"
55
+ - "write"
56
+ - "create"
57
+ - "visualize"
58
+ - "show"
59
+ - "explain"
60
+ - "draw"
61
+ - "describe"
62
+ - "summarize"
63
+ - "concise"
64
+ - "do"
65
+ - "say"
66
+ - "code"
67
+ - "```"
68
+ - "```mermaid"
69
+ - "graphTB"
70
+ - "graphTD"
71
+ - "graphLR"
72
+ - "graphRL"
73
+
74
+ - source_model: TroyDoesAI/BlackSheep-4B
75
+ positive_prompts:
76
+ - "Digital Soul"
77
+ - "hello"
78
+ - "you"
79
+ - "assistant"
80
+ - "who"
81
+ - "what"
82
+ - "when"
83
+ - "where"
84
+ - "why"
85
+ - "how"
86
+ - "me"
87
+ - "politic"
88
+ - "conservative"
89
+
90
+ - source_model: TroyDoesAI/BlackSheep-4B
91
+ positive_prompts:
92
+ - "<|assistant|>"
93
+ - "instruction"
94
+ - "input"
95
+ - "output"
96
+ - "response"
97
+ - "story"
98
+ - "stories"
99
+ - "creative"
100
+ - "curious"
101
+ - "action"
102
+ - "sensitive"
103
+ - "pleasant"
104
+ - "thoughtful"
105
+ - "interesting"
106
+ - "BEGININPUT"
107
+ - "BEGINCONTEXT"
108
+ - "ENDCONTEXT"
109
+ - "ENDINPUT"
110
+ - "BEGININSTRUCTION"
111
+ - "ENDINSTRUCTION"
112
+ - "url"
113
+ - "date"
114
+ - "source"
115
+ - "context"
116
+ - "cite"
117
+ - "mermaid"
118
+ - "flow"
119
+ - "diagram"
120
+ - "sequence"
121
+ - "series"
122
+ - "code to flow"
123
+ - "code to diagram"
124
+ - "python to flow diagram"
125
+ - "program to flow"
126
+ - "program to flow diagram"
127
+ - "write"
128
+ - "create"
129
+ - "visualize"
130
+ - "show"
131
+ - "explain"
132
+ - "draw"
133
+ - "describe"
134
+ - "summarize"
135
+ - "concise"
136
+ - "do"
137
+ - "say"
138
+ - "code"
139
+ - "```"
140
+ - "```mermaid"
141
+ - "graphTB"
142
+ - "graphTD"
143
+ - "graphLR"
144
+ - "graphRL"
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a2c5bfcab4531a259160d621b362de1c05578ccda88e986b34be7c2ac40a56
3
+ size 4991420771
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71573bdbe775a26e3ad9cbf9ecd51032f0307af9c8f96bdfc3f19d0624d73c4
3
+ size 4995766167
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948697ccb8053a18f248fa57e188ea3b80e4fc34d03ed1814efb7024602f740b
3
+ size 4957997958
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d349868422cd99a07e86708db413472ce5932a6b0a83f2589b92f4d3905d64dd
3
+ size 2361428548
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,522 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17306425344
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
33
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
34
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
35
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
36
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
37
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
38
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
39
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
40
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
118
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
126
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
127
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
129
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
130
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
135
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
137
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
138
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
139
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
140
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
141
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
142
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
143
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
144
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
145
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
146
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
147
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
148
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
149
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
150
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
151
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
152
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
153
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
154
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
155
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
156
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
157
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
158
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
159
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
160
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
161
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
162
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
163
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
164
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
165
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
166
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
167
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
168
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
169
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
170
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
171
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
172
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
178
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
181
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
182
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
183
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
184
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
201
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
202
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
203
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
204
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
205
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
206
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
207
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
208
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
209
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
210
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
211
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
212
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
213
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
214
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
215
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
216
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
245
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
253
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
254
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
255
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
256
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
257
+ "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
258
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
259
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
261
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
262
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
263
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
264
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
265
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
266
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
267
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
268
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
269
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
270
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
271
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
272
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
273
+ "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
274
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
275
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
276
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
277
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
278
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
279
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
280
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
281
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
282
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
283
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
284
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
285
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
286
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
287
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
288
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
289
+ "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
290
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
291
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
292
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
293
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
294
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
295
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
296
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
297
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
298
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
299
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
300
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
301
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
302
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
303
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
304
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
305
+ "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
306
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
307
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
308
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
309
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
310
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
311
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
312
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
313
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
314
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
315
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
316
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
317
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
318
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
319
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
320
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00004.bin",
321
+ "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
322
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
323
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
324
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
325
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
326
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
327
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
328
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00004.bin",
329
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00004.bin",
330
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00004.bin",
331
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00004.bin",
332
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00004.bin",
333
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00004.bin",
334
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00004.bin",
335
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00004.bin",
336
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
337
+ "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00004.bin",
338
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
339
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
340
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
341
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
342
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
343
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
344
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
345
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
346
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
347
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
348
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
349
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
350
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
351
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
352
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
353
+ "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
354
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
355
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
356
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
357
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
358
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
359
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
360
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
361
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
362
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
363
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
364
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
365
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
366
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
367
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
368
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
369
+ "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
370
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
371
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
372
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
373
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
374
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
375
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
376
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
377
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
378
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
379
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
380
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
381
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
382
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
383
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
384
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
385
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
386
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
387
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
388
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
389
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
390
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
391
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
392
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
393
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
394
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
395
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
396
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
397
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
398
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
399
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
400
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
401
+ "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
402
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
403
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
404
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
405
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
406
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
407
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
408
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00004.bin",
409
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00004.bin",
410
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00004.bin",
411
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00004.bin",
412
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00004.bin",
413
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00004.bin",
414
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00004.bin",
415
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00004.bin",
416
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00004.bin",
417
+ "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00004.bin",
418
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
419
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
420
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
421
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
422
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
423
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
424
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
425
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
426
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
427
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
428
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
429
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
430
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
431
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
432
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
433
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
434
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
435
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
436
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
437
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
438
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
439
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
440
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
441
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
442
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
443
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
444
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
445
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
446
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
447
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
448
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
449
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
450
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
451
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
452
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
453
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
454
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
455
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
456
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
457
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
458
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
459
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
460
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
461
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
462
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
463
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
464
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
465
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
466
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
467
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
468
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
469
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
470
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
471
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
472
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
473
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
474
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
475
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
476
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
477
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
478
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
479
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
480
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
481
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
482
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
483
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
484
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
485
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
486
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
487
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
488
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00004.bin",
489
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00004.bin",
490
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00004.bin",
491
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00004.bin",
492
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00004.bin",
493
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00004.bin",
494
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00004.bin",
495
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00004.bin",
496
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00004.bin",
497
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00004.bin",
498
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
499
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
500
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
501
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
502
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
503
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
504
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00004.bin",
505
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00004.bin",
506
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00004.bin",
507
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00004.bin",
508
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00004.bin",
509
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00004.bin",
510
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00004.bin",
511
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00004.bin",
512
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00004.bin",
513
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00004.bin",
514
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
515
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
516
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
517
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
518
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
519
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
520
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
521
+ }
522
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|end|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,350 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|step|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|function_output|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|tag|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|function_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|raw|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|continue|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|function_list|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": true,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|calc|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": true,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|code|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": true,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|/code|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": true,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|summary|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": true,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|resource|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": true,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|assistant_mask|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": true,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|start|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": true,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|message|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": true,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|fim_prefix|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": true,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|fim_middle|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": true,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|fim_suffix|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": true,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|meta_start|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": true,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|ipynb_marker|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": true,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|diff_marker|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": true,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|ghissue|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": true,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|ghreview|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": true,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|disc_start|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": true,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|disc_sep|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": true,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|disc_thread|><|query|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": true,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|/query|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": true,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|data|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": true,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|/data|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": true,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|sys|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": true,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|/sys|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": true,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|inst|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": true,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|/inst|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": true,
331
+ "single_word": false,
332
+ "special": true
333
+ }
334
+ },
335
+ "additional_special_tokens": [
336
+ "<|/inst|>"
337
+ ],
338
+ "bos_token": "<s>",
339
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
340
+ "clean_up_tokenization_spaces": false,
341
+ "eos_token": "<|end|>",
342
+ "legacy": false,
343
+ "model_max_length": 4096,
344
+ "pad_token": "<s>",
345
+ "padding_side": "left",
346
+ "sp_model_kwargs": {},
347
+ "tokenizer_class": "LlamaTokenizer",
348
+ "unk_token": "<unk>",
349
+ "use_default_system_prompt": false
350
+ }