yuzhen17 commited on
Commit
940471a
·
verified ·
1 Parent(s): 7ffcf4c

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. .gitattributes +1 -0
  2. .msc +0 -0
  3. .mv +1 -0
  4. added_tokens.json +24 -0
  5. config.json +31 -0
  6. configuration.json +1 -0
  7. generation_config.json +6 -0
  8. math_eval/aime24/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  9. math_eval/aime24/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +9 -0
  10. math_eval/aime24/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  11. math_eval/aime24/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +9 -0
  12. math_eval/amc23/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  13. math_eval/amc23/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +9 -0
  14. math_eval/amc23/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  15. math_eval/amc23/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +9 -0
  16. math_eval/gsm8k/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  17. math_eval/gsm8k/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +9 -0
  18. math_eval/gsm8k/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  19. math_eval/gsm8k/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +9 -0
  20. math_eval/math500/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  21. math_eval/math500/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +9 -0
  22. math_eval/math500/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  23. math_eval/math500/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +9 -0
  24. math_eval/minerva_math/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  25. math_eval/minerva_math/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +20 -0
  26. math_eval/minerva_math/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  27. math_eval/minerva_math/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +20 -0
  28. math_eval/olympiadbench/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl +0 -0
  29. math_eval/olympiadbench/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json +9 -0
  30. math_eval/olympiadbench/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  31. math_eval/olympiadbench/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json +9 -0
  32. pytorch_model.bin +3 -0
  33. special_tokens_map.json +31 -0
  34. tokenizer.json +3 -0
  35. tokenizer_config.json +207 -0
  36. vocab.json +0 -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
.msc ADDED
Binary file (3.52 kB). View file
 
.mv ADDED
@@ -0,0 +1 @@
 
 
1
+ Revision:master,CreatedAt:1739256077
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cfs/hadoop-aipnlp/zengweihao02/modelzoo/Qwen2.5-Math-7B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 4096,
14
+ "max_window_layers": 28,
15
+ "model_max_length": 16384,
16
+ "model_type": "qwen2",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 100000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.46.1",
27
+ "use_cache": false,
28
+ "use_mrope": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 152064
31
+ }
configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework": "pytorch", "task": "other"}
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.46.1"
6
+ }
math_eval/aime24/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/aime24/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 30.0,
7
+ "time_use_in_second": 35.265536069869995,
8
+ "time_use_in_minite": "0:35"
9
+ }
math_eval/aime24/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/aime24/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 13.3,
7
+ "time_use_in_second": 34.18890905380249,
8
+ "time_use_in_minite": "0:34"
9
+ }
math_eval/amc23/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/amc23/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 40,
3
+ "num_scores": 40,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 70.0,
7
+ "time_use_in_second": 32.98717260360718,
8
+ "time_use_in_minite": "0:32"
9
+ }
math_eval/amc23/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/amc23/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 40,
3
+ "num_scores": 40,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 62.5,
7
+ "time_use_in_second": 30.84848642349243,
8
+ "time_use_in_minite": "0:30"
9
+ }
math_eval/gsm8k/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/gsm8k/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 1319,
3
+ "num_scores": 1319,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 92.2,
7
+ "time_use_in_second": 149.93445825576782,
8
+ "time_use_in_minite": "2:29"
9
+ }
math_eval/gsm8k/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/gsm8k/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 1319,
3
+ "num_scores": 1319,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 91.0,
7
+ "time_use_in_second": 164.76103806495667,
8
+ "time_use_in_minite": "2:44"
9
+ }
math_eval/math500/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/math500/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 500,
3
+ "num_scores": 500,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 83.8,
7
+ "time_use_in_second": 98.43564033508301,
8
+ "time_use_in_minite": "1:38"
9
+ }
math_eval/math500/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/math500/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 500,
3
+ "num_scores": 500,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 83.2,
7
+ "time_use_in_second": 106.62742972373962,
8
+ "time_use_in_minite": "1:46"
9
+ }
math_eval/minerva_math/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/minerva_math/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 272,
3
+ "num_scores": 272,
4
+ "timeout_samples": 2,
5
+ "empty_samples": 1,
6
+ "acc": 39.0,
7
+ "type_acc": {
8
+ "Differential Equations (18.03 Spring 2010)": 56.2,
9
+ "Dynamics and Control (2.003 Spring 2005)": 53.8,
10
+ "Ecology I (1.018J Fall 2009)": 40.0,
11
+ "Information and Entropy (6.050J Spring 2008)": 33.3,
12
+ "Introduction to Astronomy (8.282J Spring 2006)": 37.7,
13
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 28.9,
14
+ "Physical Chemistry (5.61 Fall 2017)": 36.4,
15
+ "Principles of Microeconomics (14.01 Fall 2011)": 38.9,
16
+ "Relativity (8.033 Fall 2006)": 27.3
17
+ },
18
+ "time_use_in_second": 66.03826689720154,
19
+ "time_use_in_minite": "1:06"
20
+ }
math_eval/minerva_math/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/minerva_math/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 272,
3
+ "num_scores": 272,
4
+ "timeout_samples": 1,
5
+ "empty_samples": 0,
6
+ "acc": 30.9,
7
+ "type_acc": {
8
+ "Differential Equations (18.03 Spring 2010)": 33.3,
9
+ "Dynamics and Control (2.003 Spring 2005)": 46.2,
10
+ "Ecology I (1.018J Fall 2009)": 40.0,
11
+ "Information and Entropy (6.050J Spring 2008)": 33.3,
12
+ "Introduction to Astronomy (8.282J Spring 2006)": 26.4,
13
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 26.8,
14
+ "Physical Chemistry (5.61 Fall 2017)": 36.4,
15
+ "Principles of Microeconomics (14.01 Fall 2011)": 33.3,
16
+ "Relativity (8.033 Fall 2006)": 27.3
17
+ },
18
+ "time_use_in_second": 68.34114909172058,
19
+ "time_use_in_minite": "1:08"
20
+ }
math_eval/olympiadbench/test_o1_cot_-1_seed0_t0.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/olympiadbench/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 675,
3
+ "num_scores": 675,
4
+ "timeout_samples": 2,
5
+ "empty_samples": 0,
6
+ "acc": 46.4,
7
+ "time_use_in_second": 245.80863761901855,
8
+ "time_use_in_minite": "4:05"
9
+ }
math_eval/olympiadbench/test_o1_cot_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
math_eval/olympiadbench/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 675,
3
+ "num_scores": 675,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 47.0,
7
+ "time_use_in_second": 252.64844059944153,
8
+ "time_use_in_minite": "4:12"
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33dc2a5c7ddd38e8988a2c62fa0b9a7b58725f4fa0f476755c04256c35e314ca
3
+ size 30462579154
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33624f49f1034c4f5d92e3ec47ccdf80ccd02caf1eb1d769872ba7fb1e5be112
3
+ size 11421995
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) 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{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff