justinchuby commited on
Commit
e760a82
·
verified ·
1 Parent(s): 3aeac91

Rebuild bf16/default with per_layer_inputs contract

Browse files
bf16/default/audio_encoder/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a1a7150aa6f4bb11e01e1e47e398326b26804066fa8af3b2f1e93f17c87c509
3
- size 1210785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f6c1a64a9ddb4b728ce412aee9f908f44ffab7a5bd107e51a2857747b54113
3
+ size 1210579
bf16/default/chat_template.jinja CHANGED
@@ -295,6 +295,15 @@
295
  {%- endif -%}
296
  {%- endfor -%}
297
  {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
 
 
 
 
 
 
 
 
 
298
  {%- else -%}
299
  {{- format_tool_response_block(ns_tname.name, tool_body) -}}
300
  {%- endif -%}
 
295
  {%- endif -%}
296
  {%- endfor -%}
297
  {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
298
+ {%- for part in tool_body -%}
299
+ {%- if part.get('type') == 'image' -%}
300
+ {{- '<|image|>' -}}
301
+ {%- elif part.get('type') == 'audio' -%}
302
+ {{- '<|audio|>' -}}
303
+ {%- elif part.get('type') == 'video' -%}
304
+ {{- '<|video|>' -}}
305
+ {%- endif -%}
306
+ {%- endfor -%}
307
  {%- else -%}
308
  {{- format_tool_response_block(ns_tname.name, tool_body) -}}
309
  {%- endif -%}
bf16/default/decoder/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20688486c52341fe77322f7090fc0329a5c50c489bf7db9c702cfbb4d8e32446
3
- size 931595
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8baa2213f66382f3a0a62ccce0878c3850ec043f64028500d1af1d47fed76a46
3
+ size 849105
bf16/default/decoder/model.onnx.data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2f1f017d598d405934be2c7950b65a8d27efb6877a457d6e294d3cfe74e834e
3
- size 9458483200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d97b42fef52a524995a5c2986d2ad1781de9cd0107033cf3a9e5ad4e48f7433
3
+ size 4733337600
bf16/default/decoder/model.safetensors.index.json DELETED
@@ -1,550 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 9458465280
4
- },
5
- "weight_map": {
6
- "decoder.model.per_layer_projection_norm.weight": "model-00001-of-00002.safetensors",
7
- "decoder.model.embed_tokens_per_layer.0.weight": "model-00001-of-00002.safetensors",
8
- "decoder.model.embed_tokens_per_layer.1.weight": "model-00001-of-00002.safetensors",
9
- "decoder.model.embed_tokens_per_layer.2.weight": "model-00001-of-00002.safetensors",
10
- "decoder.model.embed_tokens_per_layer.3.weight": "model-00001-of-00002.safetensors",
11
- "decoder.model.embed_tokens_per_layer.4.weight": "model-00001-of-00002.safetensors",
12
- "decoder.model.embed_tokens_per_layer.5.weight": "model-00001-of-00002.safetensors",
13
- "decoder.model.embed_tokens_per_layer.6.weight": "model-00001-of-00002.safetensors",
14
- "decoder.model.embed_tokens_per_layer.7.weight": "model-00001-of-00002.safetensors",
15
- "decoder.model.embed_tokens_per_layer.8.weight": "model-00001-of-00002.safetensors",
16
- "decoder.model.embed_tokens_per_layer.9.weight": "model-00001-of-00002.safetensors",
17
- "decoder.model.embed_tokens_per_layer.10.weight": "model-00001-of-00002.safetensors",
18
- "decoder.model.embed_tokens_per_layer.11.weight": "model-00001-of-00002.safetensors",
19
- "decoder.model.embed_tokens_per_layer.12.weight": "model-00001-of-00002.safetensors",
20
- "decoder.model.embed_tokens_per_layer.13.weight": "model-00001-of-00002.safetensors",
21
- "decoder.model.embed_tokens_per_layer.14.weight": "model-00001-of-00002.safetensors",
22
- "decoder.model.embed_tokens_per_layer.15.weight": "model-00001-of-00002.safetensors",
23
- "decoder.model.embed_tokens_per_layer.16.weight": "model-00001-of-00002.safetensors",
24
- "decoder.model.embed_tokens_per_layer.17.weight": "model-00001-of-00002.safetensors",
25
- "decoder.model.embed_tokens_per_layer.18.weight": "model-00001-of-00002.safetensors",
26
- "decoder.model.embed_tokens_per_layer.19.weight": "model-00001-of-00002.safetensors",
27
- "decoder.model.embed_tokens_per_layer.20.weight": "model-00001-of-00002.safetensors",
28
- "decoder.model.embed_tokens_per_layer.21.weight": "model-00001-of-00002.safetensors",
29
- "decoder.model.embed_tokens_per_layer.22.weight": "model-00001-of-00002.safetensors",
30
- "decoder.model.embed_tokens_per_layer.23.weight": "model-00001-of-00002.safetensors",
31
- "decoder.model.embed_tokens_per_layer.24.weight": "model-00001-of-00002.safetensors",
32
- "decoder.model.embed_tokens_per_layer.25.weight": "model-00001-of-00002.safetensors",
33
- "decoder.model.embed_tokens_per_layer.26.weight": "model-00001-of-00002.safetensors",
34
- "decoder.model.embed_tokens_per_layer.27.weight": "model-00001-of-00002.safetensors",
35
- "decoder.model.embed_tokens_per_layer.28.weight": "model-00001-of-00002.safetensors",
36
- "decoder.model.embed_tokens_per_layer.29.weight": "model-00001-of-00002.safetensors",
37
- "decoder.model.embed_tokens_per_layer.30.weight": "model-00001-of-00002.safetensors",
38
- "decoder.model.embed_tokens_per_layer.31.weight": "model-00001-of-00002.safetensors",
39
- "decoder.model.embed_tokens_per_layer.32.weight": "model-00001-of-00002.safetensors",
40
- "decoder.model.embed_tokens_per_layer.33.weight": "model-00001-of-00002.safetensors",
41
- "decoder.model.embed_tokens_per_layer.34.weight": "model-00001-of-00002.safetensors",
42
- "decoder.model.rotary_emb_local.cos_cache": "model-00001-of-00002.safetensors",
43
- "decoder.model.rotary_emb_local.sin_cache": "model-00001-of-00002.safetensors",
44
- "decoder.model.rotary_emb_global.cos_cache": "model-00001-of-00002.safetensors",
45
- "decoder.model.rotary_emb_global.sin_cache": "model-00001-of-00002.safetensors",
46
- "decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
47
- "decoder.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
48
- "decoder.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
49
- "decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
- "decoder.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
51
- "decoder.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
52
- "decoder.model.layers.0.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
53
- "decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "decoder.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
55
- "decoder.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
56
- "decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "decoder.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
58
- "decoder.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
59
- "decoder.model.layers.1.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
60
- "decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
- "decoder.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
62
- "decoder.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
63
- "decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "decoder.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
65
- "decoder.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
- "decoder.model.layers.2.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
67
- "decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
- "decoder.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
69
- "decoder.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
70
- "decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
71
- "decoder.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
72
- "decoder.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
73
- "decoder.model.layers.3.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
74
- "decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "decoder.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
76
- "decoder.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
77
- "decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
- "decoder.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
- "decoder.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
- "decoder.model.layers.4.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
81
- "decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
- "decoder.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
- "decoder.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
84
- "decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "decoder.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
86
- "decoder.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
87
- "decoder.model.layers.5.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
88
- "decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
- "decoder.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
90
- "decoder.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
- "decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
92
- "decoder.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
93
- "decoder.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "decoder.model.layers.6.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
95
- "decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
96
- "decoder.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
97
- "decoder.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
98
- "decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
99
- "decoder.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
100
- "decoder.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
101
- "decoder.model.layers.7.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
102
- "decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "decoder.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
104
- "decoder.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
105
- "decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
- "decoder.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
107
- "decoder.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "decoder.model.layers.8.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
109
- "decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
110
- "decoder.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
111
- "decoder.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
112
- "decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
- "decoder.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
114
- "decoder.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
115
- "decoder.model.layers.9.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
116
- "decoder.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
- "decoder.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
118
- "decoder.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
119
- "decoder.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
- "decoder.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
121
- "decoder.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
122
- "decoder.model.layers.10.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
123
- "decoder.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
- "decoder.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
125
- "decoder.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
126
- "decoder.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
127
- "decoder.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "decoder.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
129
- "decoder.model.layers.11.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
130
- "decoder.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
131
- "decoder.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
132
- "decoder.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
133
- "decoder.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
- "decoder.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
135
- "decoder.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
136
- "decoder.model.layers.12.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
137
- "decoder.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
138
- "decoder.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
139
- "decoder.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
140
- "decoder.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
141
- "decoder.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
142
- "decoder.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
143
- "decoder.model.layers.13.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
144
- "decoder.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
145
- "decoder.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
146
- "decoder.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
147
- "decoder.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
- "decoder.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
149
- "decoder.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
150
- "decoder.model.layers.14.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
151
- "decoder.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
- "decoder.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
153
- "decoder.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
154
- "decoder.model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
155
- "decoder.model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
156
- "decoder.model.layers.15.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
157
- "decoder.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
158
- "decoder.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
159
- "decoder.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
160
- "decoder.model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
161
- "decoder.model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
162
- "decoder.model.layers.16.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
163
- "decoder.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
- "decoder.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
165
- "decoder.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
- "decoder.model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
167
- "decoder.model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
168
- "decoder.model.layers.17.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
169
- "decoder.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
- "decoder.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
171
- "decoder.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
172
- "decoder.model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
173
- "decoder.model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
174
- "decoder.model.layers.18.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
175
- "decoder.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
- "decoder.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
177
- "decoder.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
- "decoder.model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
179
- "decoder.model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
180
- "decoder.model.layers.19.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
181
- "decoder.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
- "decoder.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
183
- "decoder.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
- "decoder.model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
185
- "decoder.model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
186
- "decoder.model.layers.20.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
187
- "decoder.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
- "decoder.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
189
- "decoder.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
- "decoder.model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
191
- "decoder.model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
192
- "decoder.model.layers.21.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
193
- "decoder.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
- "decoder.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
195
- "decoder.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
196
- "decoder.model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
197
- "decoder.model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
198
- "decoder.model.layers.22.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
199
- "decoder.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
200
- "decoder.model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
201
- "decoder.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
- "decoder.model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
203
- "decoder.model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
204
- "decoder.model.layers.23.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
205
- "decoder.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
- "decoder.model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
207
- "decoder.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
- "decoder.model.layers.24.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
209
- "decoder.model.layers.24.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
210
- "decoder.model.layers.24.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
211
- "decoder.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
212
- "decoder.model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
213
- "decoder.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
- "decoder.model.layers.25.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
215
- "decoder.model.layers.25.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
216
- "decoder.model.layers.25.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
217
- "decoder.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
218
- "decoder.model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
219
- "decoder.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "decoder.model.layers.26.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
221
- "decoder.model.layers.26.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
222
- "decoder.model.layers.26.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
223
- "decoder.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "decoder.model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
225
- "decoder.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
226
- "decoder.model.layers.27.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
227
- "decoder.model.layers.27.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
228
- "decoder.model.layers.27.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
229
- "decoder.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
230
- "decoder.model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
231
- "decoder.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
232
- "decoder.model.layers.28.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
233
- "decoder.model.layers.28.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
234
- "decoder.model.layers.28.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
235
- "decoder.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
236
- "decoder.model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
237
- "decoder.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
- "decoder.model.layers.29.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
239
- "decoder.model.layers.29.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
240
- "decoder.model.layers.29.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
241
- "decoder.model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
- "decoder.model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
243
- "decoder.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
244
- "decoder.model.layers.30.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
245
- "decoder.model.layers.30.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
246
- "decoder.model.layers.30.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
247
- "decoder.model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
248
- "decoder.model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
249
- "decoder.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
250
- "decoder.model.layers.31.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "decoder.model.layers.31.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "decoder.model.layers.31.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
253
- "decoder.model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
254
- "decoder.model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
255
- "decoder.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
- "decoder.model.layers.32.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
257
- "decoder.model.layers.32.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
258
- "decoder.model.layers.32.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
259
- "decoder.model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
260
- "decoder.model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
261
- "decoder.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
262
- "decoder.model.layers.33.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
263
- "decoder.model.layers.33.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
264
- "decoder.model.layers.33.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
265
- "decoder.model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
266
- "decoder.model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
267
- "decoder.model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
268
- "decoder.model.layers.34.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
269
- "decoder.model.layers.34.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
270
- "decoder.model.layers.34.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
271
- "decoder.model.norm.weight": "model-00001-of-00002.safetensors",
272
- "decoder.model.per_layer_model_projection.weight_t": "model-00001-of-00002.safetensors",
273
- "decoder.model.layers.0.self_attn.q_proj.weight_t": "model-00001-of-00002.safetensors",
274
- "decoder.model.layers.0.self_attn.k_proj.weight_t": "model-00001-of-00002.safetensors",
275
- "decoder.model.layers.0.self_attn.v_proj.weight_t": "model-00001-of-00002.safetensors",
276
- "decoder.model.layers.0.self_attn.o_proj.weight_t": "model-00001-of-00002.safetensors",
277
- "decoder.model.layers.0.mlp.gate_proj.weight_t": "model-00001-of-00002.safetensors",
278
- "decoder.model.layers.0.mlp.up_proj.weight_t": "model-00001-of-00002.safetensors",
279
- "decoder.model.layers.0.mlp.down_proj.weight_t": "model-00001-of-00002.safetensors",
280
- "decoder.model.layers.0.per_layer_input_gate.weight_t": "model-00001-of-00002.safetensors",
281
- "decoder.model.layers.0.per_layer_projection.weight_t": "model-00001-of-00002.safetensors",
282
- "decoder.model.layers.1.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
283
- "decoder.model.layers.1.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
284
- "decoder.model.layers.1.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
285
- "decoder.model.layers.1.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
286
- "decoder.model.layers.1.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
287
- "decoder.model.layers.1.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
288
- "decoder.model.layers.1.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
289
- "decoder.model.layers.1.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
290
- "decoder.model.layers.1.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
291
- "decoder.model.layers.2.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
292
- "decoder.model.layers.2.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
293
- "decoder.model.layers.2.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
294
- "decoder.model.layers.2.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
295
- "decoder.model.layers.2.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
296
- "decoder.model.layers.2.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
297
- "decoder.model.layers.2.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
298
- "decoder.model.layers.2.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
299
- "decoder.model.layers.2.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
300
- "decoder.model.layers.3.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
301
- "decoder.model.layers.3.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
302
- "decoder.model.layers.3.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
303
- "decoder.model.layers.3.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
304
- "decoder.model.layers.3.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
305
- "decoder.model.layers.3.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
306
- "decoder.model.layers.3.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
307
- "decoder.model.layers.3.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
308
- "decoder.model.layers.3.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
309
- "decoder.model.layers.4.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
310
- "decoder.model.layers.4.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
311
- "decoder.model.layers.4.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
312
- "decoder.model.layers.4.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
313
- "decoder.model.layers.4.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
314
- "decoder.model.layers.4.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
315
- "decoder.model.layers.4.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
316
- "decoder.model.layers.4.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
317
- "decoder.model.layers.4.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
318
- "decoder.model.layers.5.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
319
- "decoder.model.layers.5.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
320
- "decoder.model.layers.5.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
321
- "decoder.model.layers.5.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
322
- "decoder.model.layers.5.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
323
- "decoder.model.layers.5.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
324
- "decoder.model.layers.5.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
325
- "decoder.model.layers.5.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
326
- "decoder.model.layers.5.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
327
- "decoder.model.layers.6.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
328
- "decoder.model.layers.6.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
329
- "decoder.model.layers.6.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
330
- "decoder.model.layers.6.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
331
- "decoder.model.layers.6.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
332
- "decoder.model.layers.6.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
333
- "decoder.model.layers.6.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
334
- "decoder.model.layers.6.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
335
- "decoder.model.layers.6.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
336
- "decoder.model.layers.7.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
337
- "decoder.model.layers.7.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
338
- "decoder.model.layers.7.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
339
- "decoder.model.layers.7.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
340
- "decoder.model.layers.7.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
341
- "decoder.model.layers.7.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
342
- "decoder.model.layers.7.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
343
- "decoder.model.layers.7.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
344
- "decoder.model.layers.7.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
345
- "decoder.model.layers.8.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
346
- "decoder.model.layers.8.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
347
- "decoder.model.layers.8.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
348
- "decoder.model.layers.8.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
349
- "decoder.model.layers.8.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
350
- "decoder.model.layers.8.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
351
- "decoder.model.layers.8.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
352
- "decoder.model.layers.8.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
353
- "decoder.model.layers.8.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
354
- "decoder.model.layers.9.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
355
- "decoder.model.layers.9.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
356
- "decoder.model.layers.9.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
357
- "decoder.model.layers.9.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
358
- "decoder.model.layers.9.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
359
- "decoder.model.layers.9.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
360
- "decoder.model.layers.9.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
361
- "decoder.model.layers.9.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
362
- "decoder.model.layers.9.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
363
- "decoder.model.layers.10.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
364
- "decoder.model.layers.10.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
365
- "decoder.model.layers.10.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
366
- "decoder.model.layers.10.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
367
- "decoder.model.layers.10.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
368
- "decoder.model.layers.10.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
369
- "decoder.model.layers.10.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
370
- "decoder.model.layers.10.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
371
- "decoder.model.layers.10.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
372
- "decoder.model.layers.11.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
373
- "decoder.model.layers.11.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
374
- "decoder.model.layers.11.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
375
- "decoder.model.layers.11.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
376
- "decoder.model.layers.11.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
377
- "decoder.model.layers.11.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
378
- "decoder.model.layers.11.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
379
- "decoder.model.layers.11.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
380
- "decoder.model.layers.11.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
381
- "decoder.model.layers.12.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
382
- "decoder.model.layers.12.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
383
- "decoder.model.layers.12.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
384
- "decoder.model.layers.12.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
385
- "decoder.model.layers.12.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
386
- "decoder.model.layers.12.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
387
- "decoder.model.layers.12.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
388
- "decoder.model.layers.12.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
389
- "decoder.model.layers.12.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
390
- "decoder.model.layers.13.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
391
- "decoder.model.layers.13.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
392
- "decoder.model.layers.13.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
393
- "decoder.model.layers.13.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
394
- "decoder.model.layers.13.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
395
- "decoder.model.layers.13.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
396
- "decoder.model.layers.13.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
397
- "decoder.model.layers.13.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
398
- "decoder.model.layers.13.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
399
- "decoder.model.layers.14.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
400
- "decoder.model.layers.14.self_attn.k_proj.weight_t": "model-00002-of-00002.safetensors",
401
- "decoder.model.layers.14.self_attn.v_proj.weight_t": "model-00002-of-00002.safetensors",
402
- "decoder.model.layers.14.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
403
- "decoder.model.layers.14.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
404
- "decoder.model.layers.14.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
405
- "decoder.model.layers.14.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
406
- "decoder.model.layers.14.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
407
- "decoder.model.layers.14.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
408
- "decoder.model.layers.15.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
409
- "decoder.model.layers.15.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
410
- "decoder.model.layers.15.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
411
- "decoder.model.layers.15.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
412
- "decoder.model.layers.15.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
413
- "decoder.model.layers.15.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
414
- "decoder.model.layers.15.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
415
- "decoder.model.layers.16.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
416
- "decoder.model.layers.16.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
417
- "decoder.model.layers.16.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
418
- "decoder.model.layers.16.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
419
- "decoder.model.layers.16.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
420
- "decoder.model.layers.16.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
421
- "decoder.model.layers.16.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
422
- "decoder.model.layers.17.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
423
- "decoder.model.layers.17.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
424
- "decoder.model.layers.17.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
425
- "decoder.model.layers.17.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
426
- "decoder.model.layers.17.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
427
- "decoder.model.layers.17.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
428
- "decoder.model.layers.17.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
429
- "decoder.model.layers.18.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
430
- "decoder.model.layers.18.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
431
- "decoder.model.layers.18.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
432
- "decoder.model.layers.18.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
433
- "decoder.model.layers.18.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
434
- "decoder.model.layers.18.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
435
- "decoder.model.layers.18.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
436
- "decoder.model.layers.19.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
437
- "decoder.model.layers.19.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
438
- "decoder.model.layers.19.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
439
- "decoder.model.layers.19.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
440
- "decoder.model.layers.19.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
441
- "decoder.model.layers.19.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
442
- "decoder.model.layers.19.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
443
- "decoder.model.layers.20.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
444
- "decoder.model.layers.20.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
445
- "decoder.model.layers.20.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
446
- "decoder.model.layers.20.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
447
- "decoder.model.layers.20.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
448
- "decoder.model.layers.20.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
449
- "decoder.model.layers.20.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
450
- "decoder.model.layers.21.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
451
- "decoder.model.layers.21.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
452
- "decoder.model.layers.21.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
453
- "decoder.model.layers.21.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
454
- "decoder.model.layers.21.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
455
- "decoder.model.layers.21.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
456
- "decoder.model.layers.21.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
457
- "decoder.model.layers.22.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
458
- "decoder.model.layers.22.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
459
- "decoder.model.layers.22.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
460
- "decoder.model.layers.22.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
461
- "decoder.model.layers.22.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
462
- "decoder.model.layers.22.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
463
- "decoder.model.layers.22.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
464
- "decoder.model.layers.23.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
465
- "decoder.model.layers.23.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
466
- "decoder.model.layers.23.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
467
- "decoder.model.layers.23.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
468
- "decoder.model.layers.23.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
469
- "decoder.model.layers.23.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
470
- "decoder.model.layers.23.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
471
- "decoder.model.layers.24.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
472
- "decoder.model.layers.24.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
473
- "decoder.model.layers.24.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
474
- "decoder.model.layers.24.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
475
- "decoder.model.layers.24.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
476
- "decoder.model.layers.24.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
477
- "decoder.model.layers.24.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
478
- "decoder.model.layers.25.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
479
- "decoder.model.layers.25.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
480
- "decoder.model.layers.25.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
481
- "decoder.model.layers.25.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
482
- "decoder.model.layers.25.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
483
- "decoder.model.layers.25.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
484
- "decoder.model.layers.25.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
485
- "decoder.model.layers.26.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
486
- "decoder.model.layers.26.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
487
- "decoder.model.layers.26.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
488
- "decoder.model.layers.26.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
489
- "decoder.model.layers.26.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
490
- "decoder.model.layers.26.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
491
- "decoder.model.layers.26.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
492
- "decoder.model.layers.27.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
493
- "decoder.model.layers.27.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
494
- "decoder.model.layers.27.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
495
- "decoder.model.layers.27.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
496
- "decoder.model.layers.27.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
497
- "decoder.model.layers.27.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
498
- "decoder.model.layers.27.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
499
- "decoder.model.layers.28.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
500
- "decoder.model.layers.28.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
501
- "decoder.model.layers.28.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
502
- "decoder.model.layers.28.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
503
- "decoder.model.layers.28.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
504
- "decoder.model.layers.28.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
505
- "decoder.model.layers.28.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
506
- "decoder.model.layers.29.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
507
- "decoder.model.layers.29.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
508
- "decoder.model.layers.29.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
509
- "decoder.model.layers.29.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
510
- "decoder.model.layers.29.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
511
- "decoder.model.layers.29.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
512
- "decoder.model.layers.29.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
513
- "decoder.model.layers.30.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
514
- "decoder.model.layers.30.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
515
- "decoder.model.layers.30.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
516
- "decoder.model.layers.30.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
517
- "decoder.model.layers.30.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
518
- "decoder.model.layers.30.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
519
- "decoder.model.layers.30.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
520
- "decoder.model.layers.31.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
521
- "decoder.model.layers.31.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
522
- "decoder.model.layers.31.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
523
- "decoder.model.layers.31.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
524
- "decoder.model.layers.31.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
525
- "decoder.model.layers.31.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
526
- "decoder.model.layers.31.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
527
- "decoder.model.layers.32.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
528
- "decoder.model.layers.32.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
529
- "decoder.model.layers.32.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
530
- "decoder.model.layers.32.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
531
- "decoder.model.layers.32.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
532
- "decoder.model.layers.32.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
533
- "decoder.model.layers.32.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
534
- "decoder.model.layers.33.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
535
- "decoder.model.layers.33.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
536
- "decoder.model.layers.33.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
537
- "decoder.model.layers.33.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
538
- "decoder.model.layers.33.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
539
- "decoder.model.layers.33.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
540
- "decoder.model.layers.33.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
541
- "decoder.model.layers.34.self_attn.q_proj.weight_t": "model-00002-of-00002.safetensors",
542
- "decoder.model.layers.34.self_attn.o_proj.weight_t": "model-00002-of-00002.safetensors",
543
- "decoder.model.layers.34.mlp.gate_proj.weight_t": "model-00002-of-00002.safetensors",
544
- "decoder.model.layers.34.mlp.up_proj.weight_t": "model-00002-of-00002.safetensors",
545
- "decoder.model.layers.34.mlp.down_proj.weight_t": "model-00002-of-00002.safetensors",
546
- "decoder.model.layers.34.per_layer_input_gate.weight_t": "model-00002-of-00002.safetensors",
547
- "decoder.model.layers.34.per_layer_projection.weight_t": "model-00002-of-00002.safetensors",
548
- "decoder.lm_head.weight_t": "model-00002-of-00002.safetensors"
549
- }
550
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bf16/default/embedding/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30fe32866e6ce61f44296213359b1901efd251336d77e07e9df026bd0bee5f6d
3
- size 8639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cffa34f1a4221af4cd37eb00ae30e254824c82e82fa54dda3dfd697202d6c6
3
+ size 15033
bf16/default/embedding/model.onnx.data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf8679c565c340701b4d0769edf892aa6b676c397e2c7d9e6622b4295e8db94
3
- size 805371904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3886c2dcd7d8eb8256232f3a7c16399c7a4f30be75c23eef430438e8fbc12ff
3
+ size 5530517504
bf16/default/genai_config.json CHANGED
@@ -15,7 +15,7 @@
15
  "inputs_embeds": "inputs_embeds",
16
  "attention_mask": "attention_mask",
17
  "position_ids": "position_ids",
18
- "input_ids": "input_ids",
19
  "past_key_names": "past_key_values.%d.key",
20
  "past_value_names": "past_key_values.%d.value"
21
  },
@@ -58,7 +58,8 @@
58
  "audio_features": "audio_features"
59
  },
60
  "outputs": {
61
- "inputs_embeds": "inputs_embeds"
 
62
  },
63
  "session_options": {
64
  "log_id": "onnxruntime-genai",
@@ -91,7 +92,7 @@
91
  "min_length": 0,
92
  "num_beams": 1,
93
  "num_return_sequences": 1,
94
- "past_present_share_buffer": true,
95
  "repetition_penalty": 1.0,
96
  "temperature": 1.0,
97
  "top_k": 1,
 
15
  "inputs_embeds": "inputs_embeds",
16
  "attention_mask": "attention_mask",
17
  "position_ids": "position_ids",
18
+ "per_layer_inputs": "per_layer_inputs",
19
  "past_key_names": "past_key_values.%d.key",
20
  "past_value_names": "past_key_values.%d.value"
21
  },
 
58
  "audio_features": "audio_features"
59
  },
60
  "outputs": {
61
+ "inputs_embeds": "inputs_embeds",
62
+ "per_layer_inputs": "per_layer_inputs"
63
  },
64
  "session_options": {
65
  "log_id": "onnxruntime-genai",
 
92
  "min_length": 0,
93
  "num_beams": 1,
94
  "num_return_sequences": 1,
95
+ "past_present_share_buffer": false,
96
  "repetition_penalty": 1.0,
97
  "temperature": 1.0,
98
  "top_k": 1,
bf16/default/tokenizer_config.json CHANGED
@@ -71,5 +71,5 @@
71
  "think_token": "<|think|>",
72
  "tokenizer_class": "GemmaTokenizer",
73
  "unk_token": "<unk>",
74
- "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking is defined and enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n {%- set prev_nt = namespace(role=None, found=false) -%}\n {%- if loop.index0 > 0 -%}\n {%- for j in range(loop.index0 - 1, -1, -1) -%}\n {%- if not prev_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set prev_nt.role = loop_messages[j]['role'] -%}\n {%- set prev_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message['tool_calls'] -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is string -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message['tool_responses'] -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n {%- for tc in message['tool_calls'] -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message['content'] is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message['content'] is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item['type'] == 'image' -%}\n {{- '<|image|>' -}}\n {%- set ns.prev_message_type = 'image' -%}\n {%- elif item['type'] == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- set ns.prev_message_type = 'audio' -%}\n {%- elif item['type'] == 'video' -%}\n {{- '<|video|>' -}}\n {%- set ns.prev_message_type = 'video' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif not (ns_tr_out.flag and not has_content) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- endif -%}\n{%- endif -%}"
75
  }
 
71
  "think_token": "<|think|>",
72
  "tokenizer_class": "GemmaTokenizer",
73
  "unk_token": "<unk>",
74
+ "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking is defined and enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n {%- set prev_nt = namespace(role=None, found=false) -%}\n {%- if loop.index0 > 0 -%}\n {%- for j in range(loop.index0 - 1, -1, -1) -%}\n {%- if not prev_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set prev_nt.role = loop_messages[j]['role'] -%}\n {%- set prev_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message['tool_calls'] -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is string -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message['tool_responses'] -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n {%- for tc in message['tool_calls'] -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'image' -%}\n {{- '<|image|>' -}}\n {%- elif part.get('type') == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- elif part.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message['content'] is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message['content'] is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item['type'] == 'image' -%}\n {{- '<|image|>' -}}\n {%- set ns.prev_message_type = 'image' -%}\n {%- elif item['type'] == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- set ns.prev_message_type = 'audio' -%}\n {%- elif item['type'] == 'video' -%}\n {{- '<|video|>' -}}\n {%- set ns.prev_message_type = 'video' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif not (ns_tr_out.flag and not has_content) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- endif -%}\n{%- endif -%}"
75
  }
bf16/default/vision_encoder/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9576555272bd578d33b208a795cd5d72b524d828c81ddc89ba78e14aa0edef15
3
- size 1186193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2c6ccfda6cf3c8c216ed10344c8238ce279c1170fd8ce04e2aadab32885fe2
3
+ size 1185988