Hugging Face's logo

roskosmos19
/
Rhea-4B-Coding

Text Generation
Transformers
Safetensors
English
qwen3
code
agent
Merge
uncensored
Rhea
multi-pass
reasoning
conversational
text-generation-inference
Model card Files
xet
 Community
roskosmos19 commited on
Commit
348b7c9
·
verified ·
1 Parent(s): 38f284a

Update model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +292 -404
model.safetensors.index.json CHANGED
@@ -1,406 +1,294 @@
1
  {
2
- "metadata": {
3
- "total_parameters": 4022468096,
4
- "total_size": 8044936192
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  },
6
- "weight_map": {
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
- "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
- "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
- "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
- "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
- "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
- "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
- "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
- "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
- "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
- "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
- "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
- "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
- "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
- "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
- "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
- "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
- "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
- "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
- "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
- "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
- "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
- "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
- "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
- "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
- "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
- "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
- "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
- "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
- "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
- "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
- "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
- "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
- "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
- "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
- "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
- "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
- "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
- "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
- "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
- "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
- "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
- "model.norm.weight": "model-00002-of-00002.safetensors"
405
- }
406
- }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "||<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "||<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "||<|eos|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "||<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "||<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "||<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "||<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "||<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "||<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "||<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "||<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "||<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "||<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "||<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "||<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "||<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "||<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "||<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "||<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "||<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "||<|thinking|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "||<|thinking_end|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "||<|think_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "||<|think_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "||<|review_start|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "||<|review_end|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "||<|final_start|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "||<|final_end|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ }
261
  },
262
+ "additional_special_tokens": [
263
+ "||<|im_start|>",
264
+ "||<|eos|>",
265
+ "||<|object_ref_start|>",
266
+ "||<|object_ref_end|>",
267
+ "||<|box_start|>",
268
+ "||<|box_end|>",
269
+ "||<|quad_start|>",
270
+ "||<|quad_end|>",
271
+ "||<|vision_start|>",
272
+ "||<|vision_end|>",
273
+ "||<|vision_pad|>",
274
+ "||<|image_pad|>",
275
+ "||<|video_pad|>",
276
+ "||<|think_start|>",
277
+ "||<|think_end|>",
278
+ "||<|review_start|>",
279
+ "||<|review_end|>",
280
+ "||<|final_start|>",
281
+ "||<|final_end|>"
282
+ ],
283
+ "bos_token": null,
284
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% set loop_messages = messages[1:] %}{% else %}{% set system_message = 'You are Rhea-4B, a coding AI with multi-pass processing. Your process: 1) First implementation, 2) Self-review for bugs/edge cases/security/performance, 3) Final optimized version. Functionality remains identical, only structure and comments are improved.' %}{% set loop_messages = messages %}{% endif %}{{ '||<|im_start|>system\\n' + system_message + '||<|eos|>\\n' }}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '||<|im_start|>user\\n' + message['content'] + '\\n\\n### PASS 1 - First Implementation:\\n||<|eos|>\\n' }}{% elif message['role'] == 'assistant' %}{{ '||<|im_start|>assistant\\n' + message['content'] + '\\n\\n||<|think_start|>\\n### PASS 2 - Self-Review:\\n- Syntax errors?\\n- Edge cases?\\n- Performance?\\n- Security?\\n- Type safety?\\n||<|think_end|>\\n\\n||<|review_start|>\\nReview results...\\n||<|review_end|>\\n\\n||<|final_start|>\\n### PASS 3 - Final Version:\\nBased on review - identical functionality, optimized structure:\\n\\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '||<|im_start|>assistant\\n' }}{% endif %}",
285
+ "clean_up_tokenization_spaces": false,
286
+ "eos_token": "||<|eos|>",
287
+ "errors": "replace",
288
+ "extra_special_tokens": {},
289
+ "model_max_length": 262144,
290
+ "pad_token": "||<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null
294
+ }