Hugging Face's logo

BlankZ
/
CORE_Models

Safetensors
Model card Files
xet
 Community
BlankZ commited on
Commit
dbc7c53
·
verified ·
1 Parent(s): 353bf75

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 +4 -0
  2. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_24_4567952178504e70bed891aecc7793d9.json +28 -0
  3. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_48_27fb43119f7d460d831c284c3418d2f4.json +52 -0
  4. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_24_e6054f44cdf94d3486c07c57efe5ed06.json +28 -0
  5. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_48_db997fdcfc494b9fb9d8a98503597144.json +52 -0
  6. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_24_33c1714824e9487683115a062a7846be.json +7 -0
  7. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_48_2f0c0c52e0a64c3eb98b9c10beb3322d.json +9 -0
  8. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/chat_template.jinja +1 -0
  9. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/config.json +60 -0
  10. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_0.pt +3 -0
  11. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_1.pt +3 -0
  12. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/generation_config.json +9 -0
  13. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/chat_template.jinja +1 -0
  14. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/config.json +60 -0
  15. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/special_tokens_map.json +23 -0
  16. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json +3 -0
  17. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer_config.json +194 -0
  18. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00001-of-00002.safetensors +3 -0
  19. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00002-of-00002.safetensors +3 -0
  20. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model.safetensors.index.json +347 -0
  21. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_0.pt +3 -0
  22. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_1.pt +3 -0
  23. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_0.pt +3 -0
  24. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_1.pt +3 -0
  25. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/special_tokens_map.json +23 -0
  26. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json +3 -0
  27. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer_config.json +194 -0
  28. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/data.pt +3 -0
  29. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/training_state.json +1 -0
  30. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/chat_template.jinja +1 -0
  31. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/config.json +60 -0
  32. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_0.pt +3 -0
  33. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_1.pt +3 -0
  34. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/generation_config.json +9 -0
  35. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/chat_template.jinja +1 -0
  36. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/config.json +60 -0
  37. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/special_tokens_map.json +23 -0
  38. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json +3 -0
  39. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer_config.json +194 -0
  40. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00001-of-00002.safetensors +3 -0
  41. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00002-of-00002.safetensors +3 -0
  42. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model.safetensors.index.json +347 -0
  43. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_0.pt +3 -0
  44. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_1.pt +3 -0
  45. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_0.pt +3 -0
  46. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_1.pt +3 -0
  47. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/special_tokens_map.json +23 -0
  48. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json +3 -0
  49. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer_config.json +194 -0
  50. models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/data.pt +3 -0
.gitattributes CHANGED
@@ -90,3 +90,7 @@ models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-
90
  models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
  models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
  models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
90
  models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
  models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
  models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_24_4567952178504e70bed891aecc7793d9.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "null": [
3
+ 0.75,
4
+ 0.75,
5
+ 0.75,
6
+ 0.75,
7
+ 0.75,
8
+ 0.75,
9
+ 0.75,
10
+ 0.75,
11
+ 0.75,
12
+ 0.75,
13
+ 0.75,
14
+ 0.75,
15
+ 0.75,
16
+ 0.75,
17
+ 0.75,
18
+ 0.75,
19
+ 0.75,
20
+ 0.75,
21
+ 0.75,
22
+ 0.75,
23
+ 0.75,
24
+ 0.75,
25
+ 0.75,
26
+ 0.75
27
+ ]
28
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_48_27fb43119f7d460d831c284c3418d2f4.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "null": [
3
+ 0.75,
4
+ 0.75,
5
+ 0.75,
6
+ 0.75,
7
+ 0.75,
8
+ 0.75,
9
+ 0.75,
10
+ 0.75,
11
+ 0.75,
12
+ 0.75,
13
+ 0.75,
14
+ 0.75,
15
+ 0.75,
16
+ 0.75,
17
+ 0.75,
18
+ 0.75,
19
+ 0.75,
20
+ 0.75,
21
+ 0.75,
22
+ 0.75,
23
+ 0.75,
24
+ 0.75,
25
+ 0.75,
26
+ 0.75,
27
+ 0.75,
28
+ 0.75,
29
+ 0.75,
30
+ 0.75,
31
+ 0.75,
32
+ 0.75,
33
+ 0.75,
34
+ 0.75,
35
+ 0.75,
36
+ 0.75,
37
+ 0.75,
38
+ 0.75,
39
+ 0.75,
40
+ 0.75,
41
+ 0.75,
42
+ 0.75,
43
+ 0.75,
44
+ 0.75,
45
+ 0.75,
46
+ 0.75,
47
+ 0.75,
48
+ 0.75,
49
+ 0.75,
50
+ 0.75
51
+ ]
52
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_24_e6054f44cdf94d3486c07c57efe5ed06.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "null": {
3
+ "1": 0.75,
4
+ "2": 0.75,
5
+ "3": 0.75,
6
+ "4": 0.75,
7
+ "5": 0.75,
8
+ "6": 0.75,
9
+ "7": 0.75,
10
+ "8": 0.75,
11
+ "9": 0.75,
12
+ "10": 0.75,
13
+ "11": 0.75,
14
+ "12": 0.75,
15
+ "13": 0.75,
16
+ "14": 0.75,
17
+ "15": 0.75,
18
+ "16": 0.75,
19
+ "17": 0.75,
20
+ "18": 0.75,
21
+ "19": 0.75,
22
+ "20": 0.75,
23
+ "21": 0.75,
24
+ "22": 0.75,
25
+ "23": 0.75,
26
+ "24": 0.75
27
+ }
28
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_48_db997fdcfc494b9fb9d8a98503597144.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "null": {
3
+ "1": 0.75,
4
+ "2": 0.75,
5
+ "3": 0.75,
6
+ "4": 0.75,
7
+ "5": 0.75,
8
+ "6": 0.75,
9
+ "7": 0.75,
10
+ "8": 0.75,
11
+ "9": 0.75,
12
+ "10": 0.75,
13
+ "11": 0.75,
14
+ "12": 0.75,
15
+ "13": 0.75,
16
+ "14": 0.75,
17
+ "15": 0.75,
18
+ "16": 0.75,
19
+ "17": 0.75,
20
+ "18": 0.75,
21
+ "19": 0.75,
22
+ "20": 0.75,
23
+ "21": 0.75,
24
+ "22": 0.75,
25
+ "23": 0.75,
26
+ "24": 0.75,
27
+ "25": 0.75,
28
+ "26": 0.75,
29
+ "27": 0.75,
30
+ "28": 0.75,
31
+ "29": 0.75,
32
+ "30": 0.75,
33
+ "31": 0.75,
34
+ "32": 0.75,
35
+ "33": 0.75,
36
+ "34": 0.75,
37
+ "35": 0.75,
38
+ "36": 0.75,
39
+ "37": 0.75,
40
+ "38": 0.75,
41
+ "39": 0.75,
42
+ "40": 0.75,
43
+ "41": 0.75,
44
+ "42": 0.75,
45
+ "43": 0.75,
46
+ "44": 0.75,
47
+ "45": 0.75,
48
+ "46": 0.75,
49
+ "47": 0.75,
50
+ "48": 0.75
51
+ }
52
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_24_33c1714824e9487683115a062a7846be.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "math_mcq": {
3
+ "0": 0.8288288288288288,
4
+ "10": 0.7927927927927928,
5
+ "20": 0.8198198198198198
6
+ }
7
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_48_2f0c0c52e0a64c3eb98b9c10beb3322d.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "math_mcq": {
3
+ "0": 0.8288288288288288,
4
+ "10": 0.7927927927927928,
5
+ "20": 0.8198198198198198,
6
+ "30": 0.7837837837837838,
7
+ "40": 0.7117117117117117
8
+ }
9
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.56.2",
56
+ "use_cache": true,
57
+ "use_mrope": false,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb01d1b64b654a34003addc17196e8b81d43e1a066bb2c15d87ca54a56e2b03b
3
+ size 14632
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77637b8ed17a367d02b7b9ff6ae93a58b60eee6f1612c6af22b118fc376fc23
3
+ size 14632
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.56.2"
9
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.56.2",
56
+ "use_cache": true,
57
+ "use_mrope": false,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed17ed1544b1d30831a53fe82e272920dd243d4045ffa79b855e8bde8971019
3
+ size 4996670464
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12f736b546c662e85755ca0403dd9f7f87d8b5936c6192ec646ff66a5fe0fe9
3
+ size 2111719976
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 888544000,
4
+ "total_size": 7108352000
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
260
+ "model.layers.27.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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.norm.weight": "model-00002-of-00002.safetensors"
346
+ }
347
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396de20375a72b691526204eb86c6e3c365b3cacf83eceacb45a611c185cb0ad
3
+ size 3554364602
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b50a801f5031b1cffda26fb89f93f8382b73e294902fe401e376ffe9c1ce67f
3
+ size 3554364602
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c837bc59491c120da4615d8133a0ce64030563eac5526a4a6310d212e50290
3
+ size 7108378739
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151d0a507a41387b2f6caf60772941da26d5fe4fb848b93afc84d66ab0984b6a
3
+ size 7108378739
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127ff93e90c8564e6b37caadaa51fafc71fd76e1f93d018696ee4986d62dc3d7
3
+ size 6948493
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"history_accuracy": {"null": [0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75]}, "history_accuracy_with_step": {"null": {"1": 0.75, "2": 0.75, "3": 0.75, "4": 0.75, "5": 0.75, "6": 0.75, "7": 0.75, "8": 0.75, "9": 0.75, "10": 0.75, "11": 0.75, "12": 0.75, "13": 0.75, "14": 0.75, "15": 0.75, "16": 0.75, "17": 0.75, "18": 0.75, "19": 0.75, "20": 0.75, "21": 0.75, "22": 0.75, "23": 0.75, "24": 0.75}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.8288288288288288, "10": 0.7927927927927928, "20": 0.8198198198198198}}}
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.56.2",
56
+ "use_cache": true,
57
+ "use_mrope": false,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e6ac0206ba661954dab517b9b2c4002d0c3bb83fda64488ebcbc09c2d39c47
3
+ size 14632
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9485b96a252774e4ec290005b39f029a1ea090982f715682603f2965b289938
3
+ size 14632
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.56.2"
9
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.56.2",
56
+ "use_cache": true,
57
+ "use_mrope": false,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67677b88623f5e51dc62410d3b931e60ce89e384906478f746284359488abe3f
3
+ size 4996670464
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33abe021d1685b20c0e3571a1afd0d0320f99e9a4d294e4e0f801789db8227c0
3
+ size 2111719976
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 888544000,
4
+ "total_size": 7108352000
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
260
+ "model.layers.27.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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.norm.weight": "model-00002-of-00002.safetensors"
346
+ }
347
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a46fb0eb957ffaec2fd3590c0ae6d80359bebb53396e904c7c2cf68c2685e34
3
+ size 3554364602
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65205a98c14107b19281fb4c4fc4e6a3c96558042f969ee72182aa4c919a8933
3
+ size 3554364602
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56f65f411b7267436b23fe564309b0bd272fdbe1dcc958b6effcfbb1702c32d
3
+ size 7108378739
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ca280a7a8e476e6a49b54c07ad765c359e538c7c446b9b4c602a2bafc1a700
3
+ size 7108378739
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜end▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<｜User｜>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<｜Assistant｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<｜begin▁of▁sentence｜>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<｜begin▁of▁sentence｜>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<｜end▁of▁sentence｜>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<｜end▁of▁sentence｜>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3804e816c2e6f8cff0b3ae7bd4a820e5acdeb0bbb7d18a1df74628c72a61e072
3
+ size 6948493