Hugging Face's logo

DavidAU
/
Qwen3-42B-A3B-Stranger-Thoughts-Deep20X

Text Generation
Transformers
Safetensors
qwen3_moe
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prose
vivid writing
Mixture of Experts
mixture of experts
128 experts
8 active experts
fiction
roleplaying
bfloat16
rp
qwen3
horror
finetune
thinking
reasoning
conversational
Model card Files Community
1
DavidAU commited on
Commit
b06599e
·
verified ·
1 Parent(s): 63c2ce2

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. README.md +235 -0
  3. config.json +38 -0
  4. mergekit_config.yml +207 -0
  5. model.safetensors.index.json +0 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +239 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # Qwen3-30B-A3B-Quake-pass2-bs20-2
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the Passthrough merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * D:/Qwen3-30B-A3B
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ slices:
29
+ - sources:
30
+ - model: D:/Qwen3-30B-A3B
31
+ layer_range: [0, 47]
32
+
33
+ - sources:
34
+ - model: D:/Qwen3-30B-A3B
35
+ layer_range: [47, 48]
36
+ parameters:
37
+ scale:
38
+ - filter: o_proj
39
+ value: 0.01
40
+ - filter: down_proj
41
+ value: 0.01
42
+ - value: 0.01
43
+ - sources:
44
+ - model: D:/Qwen3-30B-A3B
45
+ layer_range: [47, 48]
46
+ parameters:
47
+ scale:
48
+ - filter: o_proj
49
+ value: 0.02
50
+ - filter: down_proj
51
+ value: 0.02
52
+ - value: 0.02
53
+ - sources:
54
+ - model: D:/Qwen3-30B-A3B
55
+ layer_range: [47, 48]
56
+ parameters:
57
+ scale:
58
+ - filter: o_proj
59
+ value: 0.03
60
+ - filter: down_proj
61
+ value: 0.03
62
+ - value: 0.03
63
+ - sources:
64
+ - model: D:/Qwen3-30B-A3B
65
+ layer_range: [47, 48]
66
+ parameters:
67
+ scale:
68
+ - filter: o_proj
69
+ value: 0.04
70
+ - filter: down_proj
71
+ value: 0.04
72
+ - value: 0.04
73
+ - sources:
74
+ - model: D:/Qwen3-30B-A3B
75
+ layer_range: [47, 48]
76
+ parameters:
77
+ scale:
78
+ - filter: o_proj
79
+ value: 0.05
80
+ - filter: down_proj
81
+ value: 0.05
82
+ - value: 0.05
83
+ - sources:
84
+ - model: D:/Qwen3-30B-A3B
85
+ layer_range: [47, 48]
86
+ parameters:
87
+ scale:
88
+ - filter: o_proj
89
+ value: 0.06
90
+ - filter: down_proj
91
+ value: 0.06
92
+ - value: 0.06
93
+ - sources:
94
+ - model: D:/Qwen3-30B-A3B
95
+ layer_range: [47, 48]
96
+ parameters:
97
+ scale:
98
+ - filter: o_proj
99
+ value: 0.07
100
+ - filter: down_proj
101
+ value: 0.07
102
+ - value: 0.07
103
+ - sources:
104
+ - model: D:/Qwen3-30B-A3B
105
+ layer_range: [47, 48]
106
+ parameters:
107
+ scale:
108
+ - filter: o_proj
109
+ value: 0.08
110
+ - filter: down_proj
111
+ value: 0.08
112
+ - value: 0.08
113
+ - sources:
114
+ - model: D:/Qwen3-30B-A3B
115
+ layer_range: [47, 48]
116
+ parameters:
117
+ scale:
118
+ - filter: o_proj
119
+ value: 0.09
120
+ - filter: down_proj
121
+ value: 0.09
122
+ - value: 0.09
123
+ - sources:
124
+ - model: D:/Qwen3-30B-A3B
125
+ layer_range: [47, 48]
126
+ parameters:
127
+ scale:
128
+ - filter: o_proj
129
+ value: 0.10
130
+ - filter: down_proj
131
+ value: 0.10
132
+ - value: 0.10
133
+ - sources:
134
+ - model: D:/Qwen3-30B-A3B
135
+ layer_range: [47, 48]
136
+ parameters:
137
+ scale:
138
+ - filter: o_proj
139
+ value: 0.11
140
+ - filter: down_proj
141
+ value: 0.11
142
+ - value: .20
143
+ - sources:
144
+ - model: D:/Qwen3-30B-A3B
145
+ layer_range: [47, 48]
146
+ parameters:
147
+ scale:
148
+ - filter: o_proj
149
+ value: 0.12
150
+ - filter: down_proj
151
+ value: 0.12
152
+ - value: .21
153
+ - sources:
154
+ - model: D:/Qwen3-30B-A3B
155
+ layer_range: [47, 48]
156
+ parameters:
157
+ scale:
158
+ - filter: o_proj
159
+ value: 0.13
160
+ - filter: down_proj
161
+ value: 0.13
162
+ - value: .22
163
+ - sources:
164
+ - model: D:/Qwen3-30B-A3B
165
+ layer_range: [47, 48]
166
+ parameters:
167
+ scale:
168
+ - filter: o_proj
169
+ value: 0.14
170
+ - filter: down_proj
171
+ value: 0.14
172
+ - value: .23
173
+ - sources:
174
+ - model: D:/Qwen3-30B-A3B
175
+ layer_range: [47, 48]
176
+ parameters:
177
+ scale:
178
+ - filter: o_proj
179
+ value: 0.15
180
+ - filter: down_proj
181
+ value: 0.15
182
+ - value: .24
183
+ - sources:
184
+ - model: D:/Qwen3-30B-A3B
185
+ layer_range: [47, 48]
186
+ parameters:
187
+ scale:
188
+ - filter: o_proj
189
+ value: 0.16
190
+ - filter: down_proj
191
+ value: 0.16
192
+ - value: .4
193
+ - sources:
194
+ - model: D:/Qwen3-30B-A3B
195
+ layer_range: [47, 48]
196
+ parameters:
197
+ scale:
198
+ - filter: o_proj
199
+ value: 0.20
200
+ - filter: down_proj
201
+ value: 0.20
202
+ - value: .5
203
+ - sources:
204
+ - model: D:/Qwen3-30B-A3B
205
+ layer_range: [47, 48]
206
+ parameters:
207
+ scale:
208
+ - filter: o_proj
209
+ value: 0.25
210
+ - filter: down_proj
211
+ value: 0.25
212
+ - value: .6
213
+ - sources:
214
+ - model: D:/Qwen3-30B-A3B
215
+ layer_range: [47, 48]
216
+ parameters:
217
+ scale:
218
+ - filter: o_proj
219
+ value: 0.30
220
+ - filter: down_proj
221
+ value: 0.30
222
+ - value: .7
223
+ - sources:
224
+ - model: D:/Qwen3-30B-A3B
225
+ layer_range: [47, 48]
226
+ parameters:
227
+ scale:
228
+ - filter: o_proj
229
+ value: 0.40
230
+ - filter: down_proj
231
+ value: 0.40
232
+ - value: .8
233
+ merge_method: passthrough
234
+ dtype: bfloat16
235
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 40960,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 67,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.52.0.dev0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: D:/Qwen3-30B-A3B
4
+ layer_range: [0, 47]
5
+
6
+ - sources:
7
+ - model: D:/Qwen3-30B-A3B
8
+ layer_range: [47, 48]
9
+ parameters:
10
+ scale:
11
+ - filter: o_proj
12
+ value: 0.01
13
+ - filter: down_proj
14
+ value: 0.01
15
+ - value: 0.01
16
+ - sources:
17
+ - model: D:/Qwen3-30B-A3B
18
+ layer_range: [47, 48]
19
+ parameters:
20
+ scale:
21
+ - filter: o_proj
22
+ value: 0.02
23
+ - filter: down_proj
24
+ value: 0.02
25
+ - value: 0.02
26
+ - sources:
27
+ - model: D:/Qwen3-30B-A3B
28
+ layer_range: [47, 48]
29
+ parameters:
30
+ scale:
31
+ - filter: o_proj
32
+ value: 0.03
33
+ - filter: down_proj
34
+ value: 0.03
35
+ - value: 0.03
36
+ - sources:
37
+ - model: D:/Qwen3-30B-A3B
38
+ layer_range: [47, 48]
39
+ parameters:
40
+ scale:
41
+ - filter: o_proj
42
+ value: 0.04
43
+ - filter: down_proj
44
+ value: 0.04
45
+ - value: 0.04
46
+ - sources:
47
+ - model: D:/Qwen3-30B-A3B
48
+ layer_range: [47, 48]
49
+ parameters:
50
+ scale:
51
+ - filter: o_proj
52
+ value: 0.05
53
+ - filter: down_proj
54
+ value: 0.05
55
+ - value: 0.05
56
+ - sources:
57
+ - model: D:/Qwen3-30B-A3B
58
+ layer_range: [47, 48]
59
+ parameters:
60
+ scale:
61
+ - filter: o_proj
62
+ value: 0.06
63
+ - filter: down_proj
64
+ value: 0.06
65
+ - value: 0.06
66
+ - sources:
67
+ - model: D:/Qwen3-30B-A3B
68
+ layer_range: [47, 48]
69
+ parameters:
70
+ scale:
71
+ - filter: o_proj
72
+ value: 0.07
73
+ - filter: down_proj
74
+ value: 0.07
75
+ - value: 0.07
76
+ - sources:
77
+ - model: D:/Qwen3-30B-A3B
78
+ layer_range: [47, 48]
79
+ parameters:
80
+ scale:
81
+ - filter: o_proj
82
+ value: 0.08
83
+ - filter: down_proj
84
+ value: 0.08
85
+ - value: 0.08
86
+ - sources:
87
+ - model: D:/Qwen3-30B-A3B
88
+ layer_range: [47, 48]
89
+ parameters:
90
+ scale:
91
+ - filter: o_proj
92
+ value: 0.09
93
+ - filter: down_proj
94
+ value: 0.09
95
+ - value: 0.09
96
+ - sources:
97
+ - model: D:/Qwen3-30B-A3B
98
+ layer_range: [47, 48]
99
+ parameters:
100
+ scale:
101
+ - filter: o_proj
102
+ value: 0.10
103
+ - filter: down_proj
104
+ value: 0.10
105
+ - value: 0.10
106
+ - sources:
107
+ - model: D:/Qwen3-30B-A3B
108
+ layer_range: [47, 48]
109
+ parameters:
110
+ scale:
111
+ - filter: o_proj
112
+ value: 0.11
113
+ - filter: down_proj
114
+ value: 0.11
115
+ - value: .20
116
+ - sources:
117
+ - model: D:/Qwen3-30B-A3B
118
+ layer_range: [47, 48]
119
+ parameters:
120
+ scale:
121
+ - filter: o_proj
122
+ value: 0.12
123
+ - filter: down_proj
124
+ value: 0.12
125
+ - value: .21
126
+ - sources:
127
+ - model: D:/Qwen3-30B-A3B
128
+ layer_range: [47, 48]
129
+ parameters:
130
+ scale:
131
+ - filter: o_proj
132
+ value: 0.13
133
+ - filter: down_proj
134
+ value: 0.13
135
+ - value: .22
136
+ - sources:
137
+ - model: D:/Qwen3-30B-A3B
138
+ layer_range: [47, 48]
139
+ parameters:
140
+ scale:
141
+ - filter: o_proj
142
+ value: 0.14
143
+ - filter: down_proj
144
+ value: 0.14
145
+ - value: .23
146
+ - sources:
147
+ - model: D:/Qwen3-30B-A3B
148
+ layer_range: [47, 48]
149
+ parameters:
150
+ scale:
151
+ - filter: o_proj
152
+ value: 0.15
153
+ - filter: down_proj
154
+ value: 0.15
155
+ - value: .24
156
+ - sources:
157
+ - model: D:/Qwen3-30B-A3B
158
+ layer_range: [47, 48]
159
+ parameters:
160
+ scale:
161
+ - filter: o_proj
162
+ value: 0.16
163
+ - filter: down_proj
164
+ value: 0.16
165
+ - value: .4
166
+ - sources:
167
+ - model: D:/Qwen3-30B-A3B
168
+ layer_range: [47, 48]
169
+ parameters:
170
+ scale:
171
+ - filter: o_proj
172
+ value: 0.20
173
+ - filter: down_proj
174
+ value: 0.20
175
+ - value: .5
176
+ - sources:
177
+ - model: D:/Qwen3-30B-A3B
178
+ layer_range: [47, 48]
179
+ parameters:
180
+ scale:
181
+ - filter: o_proj
182
+ value: 0.25
183
+ - filter: down_proj
184
+ value: 0.25
185
+ - value: .6
186
+ - sources:
187
+ - model: D:/Qwen3-30B-A3B
188
+ layer_range: [47, 48]
189
+ parameters:
190
+ scale:
191
+ - filter: o_proj
192
+ value: 0.30
193
+ - filter: down_proj
194
+ value: 0.30
195
+ - value: .7
196
+ - sources:
197
+ - model: D:/Qwen3-30B-A3B
198
+ layer_range: [47, 48]
199
+ parameters:
200
+ scale:
201
+ - filter: o_proj
202
+ value: 0.40
203
+ - filter: down_proj
204
+ value: 0.40
205
+ - value: .8
206
+ merge_method: passthrough
207
+ dtype: bfloat16
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
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": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }