lucyknada commited on
Commit
6815390
1 Parent(s): 0ca1d58

Upload folder using huggingface_hub

Browse files
.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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/data/gemma-2-9b-chatml",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 8,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 42,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 0,
25
+ "query_pre_attn_scalar": 256,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 10000.0,
28
+ "sliding_window": 4096,
29
+ "sliding_window_size": 4096,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.45.0.dev0",
32
+ "use_cache": false,
33
+ "vocab_size": 256000
34
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "do_sample": true,
6
+ "eos_token_id": 8,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.45.0.dev0"
9
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step752
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99b000e0a36149bd286c7acabb042800e65bc51b023280f8f0b877d68c8c3d4
3
+ size 4903351912
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa8548a2388260d78b07352b4be7e113ff11b9669713cc1f3a782f1f4b6b1bf
3
+ size 4947570872
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cbbe404a3384cba094ad1f1b999b93bd68594e4d8de82adf7d3e17edfd0b9a
3
+ size 4962221464
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0622dca8062a5947d9c84794ad853859a73e0951a9085f232432bcbe8545fc57
3
+ size 3670322200
model.safetensors.index.json ADDED
@@ -0,0 +1,471 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18483411968
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
294
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
295
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
298
+ "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
305
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
316
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
317
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
319
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
321
+ "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
324
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
326
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
335
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
338
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
341
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
343
+ "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
344
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
345
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
346
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
347
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
348
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
349
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
350
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
351
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
353
+ "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
354
+ "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
355
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
356
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
357
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
358
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
359
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
360
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
363
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
365
+ "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
366
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
367
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
368
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
369
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
370
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
371
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
372
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
373
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
374
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
375
+ "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
376
+ "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
377
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
378
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
379
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
380
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
381
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
393
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
394
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
395
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
396
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
397
+ "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
398
+ "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
399
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
400
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
401
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
402
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
403
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
404
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
405
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
406
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
407
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
408
+ "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
409
+ "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
410
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
411
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
412
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
413
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
414
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
415
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
416
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
417
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
418
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
419
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
420
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
421
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
422
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
423
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
424
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
425
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
426
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
427
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
428
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
429
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
430
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
431
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
432
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
433
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
434
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
435
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
436
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
437
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
438
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
439
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
442
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
443
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
444
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
445
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
446
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
447
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
448
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
449
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
450
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
451
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
452
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
453
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
454
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
455
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
456
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
457
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
458
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
459
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
460
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
461
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
462
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
463
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
464
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
465
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
466
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
467
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
468
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
469
+ "model.norm.weight": "model-00004-of-00004.safetensors"
470
+ }
471
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7d2783779c7a0fcbff8931e552ed350f4462104b30708eb4e72a7105b48dc1
3
+ size 17518532
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f545c6099874ce0c5cf6e4ccecd5f2bce689852b576ddf9d49134081c9cb98
3
+ size 4241007
tokenizer_config.json ADDED
@@ -0,0 +1,1757 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<|im_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<|im_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ }
1741
+ },
1742
+ "additional_special_tokens": [
1743
+ "<start_of_turn>",
1744
+ "<end_of_turn>"
1745
+ ],
1746
+ "bos_token": "<bos>",
1747
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
1748
+ "clean_up_tokenization_spaces": false,
1749
+ "eos_token": "<|im_end|>",
1750
+ "model_max_length": 1000000000000000019884624838656,
1751
+ "pad_token": "<pad>",
1752
+ "sp_model_kwargs": {},
1753
+ "spaces_between_special_tokens": false,
1754
+ "tokenizer_class": "GemmaTokenizer",
1755
+ "unk_token": "<unk>",
1756
+ "use_default_system_prompt": false
1757
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``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``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``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``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``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``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)