TroyDoesAI commited on
Commit
a2016d5
·
verified ·
1 Parent(s): 66dcc13
added_tokens.json CHANGED
@@ -1,40 +1,40 @@
1
- {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
- "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
- "<|endoftext|>": 32000,
18
- "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
- "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
- "<|user|>": 32010
40
- }
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
config.json CHANGED
@@ -1,27 +1,30 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 32000,
9
- "hidden_act": "silu",
10
- "hidden_size": 3072,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 8192,
13
- "max_position_embeddings": 131072,
14
- "model_type": "llama",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 32,
18
- "rms_norm_eps": 1e-05,
19
- "rope_scaling": null,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 2047,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.40.0.dev0",
25
- "use_cache": true,
26
- "vocab_size": 32064
27
- }
 
 
 
 
1
+ {
2
+ "_name_or_path": ".\\Mini",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "sliding_window": 2047,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.41.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32064
30
+ }
generation_config.json CHANGED
@@ -1,10 +1,10 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": [
5
- 32000,
6
- 32007
7
- ],
8
- "pad_token_id": 32000,
9
- "transformers_version": "4.39.3"
10
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32007
7
+ ],
8
+ "pad_token_id": 32000,
9
+ "transformers_version": "4.41.2"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376ee858014fa703c7ea0af390548026b7c65cec89205852234bc56984732ba4
3
+ size 4991370776
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa5ccdba6a4e19ffc7edaa6f37ad4c0ad9c625a320b6a494a6a67003827ee85
3
+ size 2650821720
model.safetensors.index.json CHANGED
@@ -1,299 +1,298 @@
1
- {
2
- "metadata": {
3
- "total_size": 7642192792
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00001-of-00001.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00001-of-00001.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00001-of-00001.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00001-of-00001.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00001-of-00001.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00001-of-00001.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
296
- "model.norm.weight": "model-00001-of-00001.safetensors"
297
- }
298
- }
299
-
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7642159104
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
 
special_tokens_map.json CHANGED
@@ -1,33 +1,33 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
- "bos_token": {
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<|endoftext|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|end|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json CHANGED
@@ -476,6 +476,7 @@
476
  "end_of_word_suffix": null,
477
  "fuse_unk": true,
478
  "byte_fallback": true,
 
479
  "vocab": {
480
  "<unk>": 0,
481
  "<s>": 1,
 
476
  "end_of_word_suffix": null,
477
  "fuse_unk": true,
478
  "byte_fallback": true,
479
+ "ignore_merges": false,
480
  "vocab": {
481
  "<unk>": 0,
482
  "<s>": 1,
tokenizer_config.json CHANGED
@@ -1,349 +1,349 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": true,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "32000": {
30
- "content": "<|endoftext|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|assistant|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": true,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32002": {
46
- "content": "<|step|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|function_output|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|tag|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|function_call|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": true,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "32006": {
78
- "content": "<|system|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|raw|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|continue|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": true,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "32010": {
110
- "content": "<|user|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
- "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
- "clean_up_tokenization_spaces": false,
340
- "eos_token": "<|end|>",
341
- "legacy": false,
342
- "model_max_length": 4096,
343
- "pad_token": "<|endoftext|>",
344
- "padding_side": "left",
345
- "sp_model_kwargs": {},
346
- "tokenizer_class": "LlamaTokenizer",
347
- "unk_token": "<unk>",
348
- "use_default_system_prompt": false
349
- }
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|step|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|function_output|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|tag|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|function_call|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|raw|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|continue|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|function_list|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|calc|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|code|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|/code|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|summary|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|resource|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|assistant_mask|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|start|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|message|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|fim_prefix|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|fim_middle|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|fim_suffix|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|meta_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|ipynb_marker|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|diff_marker|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|ghissue|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|ghreview|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|disc_start|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|disc_sep|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|disc_thread|><|query|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|/query|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|data|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|/data|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|sys|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|/sys|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|inst|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/inst|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ }
333
+ },
334
+ "additional_special_tokens": [
335
+ "<|/inst|>"
336
+ ],
337
+ "bos_token": "<s>",
338
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
+ "clean_up_tokenization_spaces": false,
340
+ "eos_token": "<|end|>",
341
+ "legacy": false,
342
+ "model_max_length": 4096,
343
+ "pad_token": "<|endoftext|>",
344
+ "padding_side": "left",
345
+ "sp_model_kwargs": {},
346
+ "tokenizer_class": "LlamaTokenizer",
347
+ "unk_token": "<unk>",
348
+ "use_default_system_prompt": false
349
+ }