MilaWang commited on
Commit
3ff5625
·
verified ·
1 Parent(s): d2072d8

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +21 -0
  2. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/added_tokens.json +24 -0
  11. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/config.json +31 -0
  12. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/merges.txt +0 -0
  13. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/special_tokens_map.json +31 -0
  14. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/tokenizer.json +3 -0
  15. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/tokenizer_config.json +208 -0
  16. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/vocab.json +0 -0
  17. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_0.pt +3 -0
  18. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_1.pt +3 -0
  19. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_2.pt +3 -0
  20. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_3.pt +3 -0
  21. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_4.pt +3 -0
  22. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_5.pt +3 -0
  23. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_6.pt +3 -0
  24. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_7.pt +3 -0
  25. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_0.pt +3 -0
  26. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_1.pt +3 -0
  27. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_2.pt +3 -0
  28. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_3.pt +3 -0
  29. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_4.pt +3 -0
  30. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_5.pt +3 -0
  31. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_6.pt +3 -0
  32. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_7.pt +3 -0
  33. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/data.pt +3 -0
  34. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_0.pt +3 -0
  35. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_1.pt +3 -0
  36. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_2.pt +3 -0
  37. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_3.pt +3 -0
  38. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_4.pt +3 -0
  39. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_5.pt +3 -0
  40. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_6.pt +3 -0
  41. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_7.pt +3 -0
  42. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/added_tokens.json +24 -0
  43. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/config.json +31 -0
  44. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/merges.txt +0 -0
  45. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/special_tokens_map.json +31 -0
  46. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/tokenizer.json +3 -0
  47. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/tokenizer_config.json +208 -0
  48. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/vocab.json +0 -0
  49. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/model_world_size_8_rank_0.pt +3 -0
  50. es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/model_world_size_8_rank_1.pt +3 -0
.gitattributes CHANGED
@@ -75,3 +75,24 @@ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tok
75
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_400_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_400_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
  es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1360/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1440/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1760/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1840/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1920/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2000/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2080/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2160/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2240/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2320_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2400/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_480/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_560/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_720/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_800/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ es-qwen-math-base-7b-3k-40k-ds_o2/global_step_880/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8f899882452e2546b59dd22b4b598309405b31b18b4fa66c716cc8fa65b526
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79f82864db174542939d91e8b2134d8d3826434f16d45657214de42e18c5283
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d459359829dd015db7eb29d981ccab2af63acc58afa9d605751bfb2ed838cce4
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffde0ef20ea813d2b3994849d0350e7eb5cb84e3fbbd730022cf564b456e1c9
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49775649737a2abfb9d73a97b86e727e78e86cdb8fef5e15b5ec58ff86b6da8
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f15b4df3e14e335a83db2db5f5aaa7ac66eb438c41451d453738edacdce5b81
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e706ec22aa8d7f6b20b34f4a64cb85b7635789324b66cd0cf616eb882329e9f
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e592947b2e15e30e89c50e90c41e6021ec0037df26defe1fe8dc3112267ba1
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/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
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "Qwen/Qwen2.5-Math-7B",
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
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_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "sliding_window": 4096,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.49.0",
27
+ "use_cache": true,
28
+ "use_mrope": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 152064
31
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/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": "<|endoftext|>",
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
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4924911f0c368851ad50ea207c7c5ceef3eaae69914376fe1106b83231f40c
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77689f0cf4e0d344dc53981133f43e1636ad7ac2d49140124c467be2611d2b70
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff926f017b3f15f988af8e203b9f1454959bd1043843f01abc1d1d92e4e5913
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9de5819e835c4b233f50a5abc233af1d304da40379fa4ec4448d16c3728e18
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2510c45733fbec966938731c2bc3e88835effa66d2f6866ea045539262b5ae00
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b5c1e747a79b2dc0aa8e6a35db3961893506c11f56fd9185123d3731f8805a
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0499b32f7e2a1f1c8578ccd8dfde18c2c28db8e9f88801e6da37187c9e1ada8
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:783c05d3c4a6a3dc359ed4deff68abc7254752ea789839648e109451a4754b6b
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cca3ed634715ba9c1dce9ec8c8c3047850cba121dfbc2de2138ffbe6226c979
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca90d3c29d7a71363c6495a6a22695c06ae09b9544d4835161534e879101993
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f22fdaa79b7280ae19bee23c16d722bcd65ab4a8586dd1e692e02db232ebaf
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09475bf204bbe738adf0c834aec3bbff53a94e7ec055928b9e929ea19d9610f6
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad7c7e813ec43b47c7b6fad66a297ad37ab963d7cd6a764bf712555ab5ad51f
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e377a7b2b64d011b5e955db16280fb4c360c8bceb3198c3350ec6f771f80bb47
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4605ce4b4fdbae7cae69ee5b55b264a0bc7a31ea508dc5881fa319a7acb7d2
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cade052da1efe9dfc5f190766c1f16710ed5d1e45d243c3ae7f25f3e2e55881
3
+ size 7615643215
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1040/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b747e476d8fe3fb21b5c11b65488beea0a4b2a12c3a23d8ea572cf8c9fb8c46
3
+ size 6948493
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ec69d214605828638e6bf6e564e55b2b0f5593d24fac50ff2b2f3e4b81673a
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807f0f5cd0c7fe433184b77bfa3fd2cdfa15f4164a438c640de0099515d15092
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c189fed88317d539ae994d61607f35b41b2ee39d18876dd0d4c0c903753a35ac
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af7a0171b091ba81fbbd33ab531f86137430c5724e3136bdb87dee192f4b518
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6dba0cc25219c0db6f7b40b461be696a171da925a04ba0ff4e8349636993b7
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d38b04ab491d1d63d9cc5bf82f4b0dbb0889e19ea96641ad9dd4e359e8bace
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed0aab3fc2be93e7d2711a01129e8b3c0cb49b8cc08bd625ec85e2c9944bc66
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025a3fd7cca44a08c66bbd54434e9a90c6af607d6d099ed03e2f1c7f3a6268c3
3
+ size 14632
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/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
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "Qwen/Qwen2.5-Math-7B",
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
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_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "sliding_window": 4096,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.49.0",
27
+ "use_cache": true,
28
+ "use_mrope": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 152064
31
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/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": "<|endoftext|>",
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
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffa109fe1624fdac4430f440d0b11bbe73c35ff8b01b2c019da7c428b656425
3
+ size 3807995194
es-qwen-math-base-7b-3k-40k-ds_o2/global_step_1120/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1416633d07e8e028d4cd1f4d24d1c9a0e2beff590ba7b1535a0cd8b87ba443
3
+ size 3807995194