stallone commited on
Commit
0840c2a
1 Parent(s): 2bf5c58

Model upload

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|end_of_role|>": 49153,
3
+ "<|start_of_role|>": 49152,
4
+ "<|tool_call|>": 49154
5
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.015625,
8
+ "bos_token_id": 0,
9
+ "embedding_multiplier": 12.0,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1536,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "logits_scaling": 6.0,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "granitemoe",
18
+ "num_attention_heads": 24,
19
+ "num_experts_per_tok": 8,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 8,
22
+ "num_local_experts": 40,
23
+ "output_router_logits": false,
24
+ "pad_token_id": 0,
25
+ "residual_multiplier": 0.22,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000,
29
+ "router_aux_loss_coef": 0.001,
30
+ "tie_word_embeddings": true,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.46.0.dev0",
33
+ "use_cache": true,
34
+ "vocab_size": 49155
35
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4b5d32528dd83b2e16c9464eab012e22879170d55b789dafb641f5121feedd
3
+ size 4998548704
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c72ed00f001f574671714b6c175bea900d5e4b797327aa94d52027098cb815
3
+ size 1750077728
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6748591104
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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
143
+ "model.layers.22.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.input_layernorm.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-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.input_layernorm.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.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.input_layernorm.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 ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_of_role|>",
4
+ "<|end_of_role|>",
5
+ "<|tool_call|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|end_of_text|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|end_of_text|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<|end_of_text|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<|end_of_text|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|end_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<issue_start>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<issue_comment>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<issue_closed>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<jupyter_start>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<jupyter_text>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<jupyter_code>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<jupyter_output>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<empty_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<commit_before>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<commit_msg>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<commit_after>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<reponame>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "49152": {
158
+ "content": "<|start_of_role|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "49153": {
166
+ "content": "<|end_of_role|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "49154": {
174
+ "content": "<|tool_call|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|start_of_role|>",
184
+ "<|end_of_role|>",
185
+ "<|tool_call|>"
186
+ ],
187
+ "bos_token": "<|end_of_text|>",
188
+ "chat_template": "{%- if tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>\n' }}\n {%- for tool in tools %}\n {{- tool | tojson(indent=4) }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- endif %}\n {%- endfor %}\n {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {{- '<|start_of_role|>system<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'user' %}\n {{- '<|start_of_role|>user<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'tool_response' %}\n {{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}",
189
+ "clean_up_tokenization_spaces": true,
190
+ "eos_token": "<|end_of_text|>",
191
+ "errors": "replace",
192
+ "model_max_length": 9223372036854775807,
193
+ "pad_token": "<|end_of_text|>",
194
+ "padding_side": "left",
195
+ "tokenizer_class": "GPT2Tokenizer",
196
+ "unk_token": "<|end_of_text|>",
197
+ "vocab_size": 49152
198
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff