Hugging Face's logo

loraes
/
full_es_model

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
ljq34952 commited on
Commit
5e30fed
·
1 Parent(s): d7dc81f

add model 3

Browse files
Files changed (39) hide show
  1. Qwen2.5-1.5B-FULL-ES-1/history.json +0 -0
  2. Qwen2.5-1.5B-FULL-ES-1/merged/added_tokens.json +3 -24
  3. Qwen2.5-1.5B-FULL-ES-1/merged/config.json +3 -62
  4. Qwen2.5-1.5B-FULL-ES-1/merged/special_tokens_map.json +3 -31
  5. Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer_config.json +3 -207
  6. Qwen2.5-1.5B-FULL-ES-1/merged/vocab.json +0 -0
  7. Qwen2.5-1.5B-FULL-ES-2/history.json +0 -0
  8. Qwen2.5-1.5B-FULL-ES-2/merged/added_tokens.json +3 -24
  9. Qwen2.5-1.5B-FULL-ES-2/merged/config.json +3 -62
  10. Qwen2.5-1.5B-FULL-ES-2/merged/special_tokens_map.json +3 -31
  11. Qwen2.5-1.5B-FULL-ES-2/merged/tokenizer_config.json +3 -207
  12. Qwen2.5-1.5B-FULL-ES-2/merged/vocab.json +0 -0
  13. Qwen2.5-1.5B-R16-s0.0225-a0.0025/config.yaml +40 -0
  14. Qwen2.5-1.5B-R16-s0.0225-a0.0025/history.json +3 -0
  15. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/added_tokens.json +3 -0
  16. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/chat_template.jinja +54 -0
  17. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/config.json +3 -0
  18. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/merges.txt +0 -0
  19. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/model.safetensors +3 -0
  20. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/special_tokens_map.json +3 -0
  21. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/tokenizer.json +3 -0
  22. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/tokenizer_config.json +3 -0
  23. Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/vocab.json +3 -0
  24. Qwen2.5-1.5B-R16-s0.0225-a0.0025/tensorboard/events.out.tfevents.1779981759.sys-421gu-tnxr.2863017.0 +3 -0
  25. Qwen2.5-1.5B-R16-s0.0225-a0.0035/config.yaml +40 -0
  26. Qwen2.5-1.5B-R16-s0.0225-a0.0035/history.json +3 -0
  27. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/added_tokens.json +3 -0
  28. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/chat_template.jinja +54 -0
  29. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/config.json +3 -0
  30. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/merges.txt +0 -0
  31. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/model.safetensors +3 -0
  32. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/special_tokens_map.json +3 -0
  33. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/tokenizer.json +3 -0
  34. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/tokenizer_config.json +3 -0
  35. Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/vocab.json +3 -0
  36. Qwen2.5-1.5B-R16-s0.0225-a0.0035/tensorboard/events.out.tfevents.1779981759.sys-421gu-tnxr.2863018.0 +3 -0
  37. Qwen2.5-1.5B-R16-s0.0225-a0.005/history.json +3 -0
  38. Qwen2.5-1.5B-R16-s0.0225-a0.005/merged +1 -0
  39. Qwen2.5-1.5B-R16-s0.0225-a0.005/tensorboard/events.out.tfevents.1779897887.sys-421gu-tnxr.3547822.0 +3 -0
Qwen2.5-1.5B-FULL-ES-1/history.json CHANGED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-FULL-ES-1/merged/added_tokens.json CHANGED
@@ -1,24 +1,3 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/merged/config.json CHANGED
@@ -1,62 +1,3 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 151645,
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": 32768,
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
- "rms_norm_eps": 1e-06,
50
- "rope_parameters": {
51
- "rope_theta": 1000000.0,
52
- "rope_type": "default"
53
- },
54
- "rope_scaling": null,
55
- "rope_theta": 1000000.0,
56
- "sliding_window": null,
57
- "tie_word_embeddings": true,
58
- "transformers_version": "4.57.6",
59
- "use_cache": true,
60
- "use_sliding_window": false,
61
- "vocab_size": 151936
62
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c056f4a27d910748710a6cfb66061c3a2d36ca5b2ff0c7df9380cd17bf9e2d2b
3
+ size 1400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/merged/special_tokens_map.json CHANGED
@@ -1,31 +1,3 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer_config.json CHANGED
@@ -1,207 +1,3 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- }
181
- },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
- "bos_token": null,
198
- "clean_up_tokenization_spaces": false,
199
- "eos_token": "<|im_end|>",
200
- "errors": "replace",
201
- "extra_special_tokens": {},
202
- "model_max_length": 131072,
203
- "pad_token": "<|endoftext|>",
204
- "split_special_tokens": false,
205
- "tokenizer_class": "Qwen2Tokenizer",
206
- "unk_token": null
207
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
3
+ size 4686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/merged/vocab.json CHANGED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-FULL-ES-2/history.json CHANGED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-FULL-ES-2/merged/added_tokens.json CHANGED
@@ -1,24 +1,3 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-2/merged/config.json CHANGED
@@ -1,62 +1,3 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 151645,
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": 32768,
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
- "rms_norm_eps": 1e-06,
50
- "rope_parameters": {
51
- "rope_theta": 1000000.0,
52
- "rope_type": "default"
53
- },
54
- "rope_scaling": null,
55
- "rope_theta": 1000000.0,
56
- "sliding_window": null,
57
- "tie_word_embeddings": true,
58
- "transformers_version": "4.57.6",
59
- "use_cache": true,
60
- "use_sliding_window": false,
61
- "vocab_size": 151936
62
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c056f4a27d910748710a6cfb66061c3a2d36ca5b2ff0c7df9380cd17bf9e2d2b
3
+ size 1400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-2/merged/special_tokens_map.json CHANGED
@@ -1,31 +1,3 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-2/merged/tokenizer_config.json CHANGED
@@ -1,207 +1,3 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- }
181
- },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
- "bos_token": null,
198
- "clean_up_tokenization_spaces": false,
199
- "eos_token": "<|im_end|>",
200
- "errors": "replace",
201
- "extra_special_tokens": {},
202
- "model_max_length": 131072,
203
- "pad_token": "<|endoftext|>",
204
- "split_special_tokens": false,
205
- "tokenizer_class": "Qwen2Tokenizer",
206
- "unk_token": null
207
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
3
+ size 4686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-2/merged/vocab.json CHANGED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-R16-s0.0225-a0.0025/config.yaml ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ es:
2
+ n_epochs: 10
3
+ batch_size: 100
4
+ sigma: 0.0225
5
+ alpha: 0.0025
6
+ pop_size: 60
7
+ reward_normalization: zscore
8
+ schedule_mode: keep_tail_per_epoch
9
+ reward_normalization_ddof: 0
10
+ reward_normalization_eps: 1.0e-08
11
+ sync_engines_on_validate: false
12
+ sync_engine_reference: 0
13
+ raw_train_size: 7473
14
+ effective_train_size: 7473
15
+ max_steps: 750
16
+ config_version: 2
17
+ method: es
18
+ finetune:
19
+ type: lora
20
+ lora_rank: 16
21
+ lora_alpha: 16
22
+ target_modules:
23
+ - q_proj
24
+ - v_proj
25
+ method_params: {}
26
+ output:
27
+ seed: 42
28
+ dir: /home/zhi/ljq/ES4LLM/curves/lora/r16/20260528_151958_2862980/sigma0.0225_alpha0.0025
29
+ dtype: bfloat16
30
+ benchmark: gsm8k
31
+ gsm8k_path: /home/zhi/ES4LLM-main/data/dataset/gsm8k
32
+ checkpoint:
33
+ save_freq: 50
34
+ export_merged_freq: 50
35
+ generation:
36
+ max_new_tokens: 2048
37
+ format_reward: 0.1
38
+ model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
39
+ runtime:
40
+ model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
Qwen2.5-1.5B-R16-s0.0225-a0.0025/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83602a7f64a7fce2368bcc6224b62450b133909ce6010d7e89a60dc8ed8c72c8
3
+ size 99948
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c056f4a27d910748710a6cfb66061c3a2d36ca5b2ff0c7df9380cd17bf9e2d2b
3
+ size 1400
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39177fc7e5825f5bbe0a30b96fc964c1cccd188ca6e65c820f0b675a5c119aab
3
+ size 3554214720
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
3
+ size 4686
Qwen2.5-1.5B-R16-s0.0225-a0.0025/merged/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
Qwen2.5-1.5B-R16-s0.0225-a0.0025/tensorboard/events.out.tfevents.1779981759.sys-421gu-tnxr.2863017.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f28c1bcd583e67db20aa5df60242e374320317a27660350b0a4ea0374c76c0
3
+ size 126977
Qwen2.5-1.5B-R16-s0.0225-a0.0035/config.yaml ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ es:
2
+ n_epochs: 10
3
+ batch_size: 100
4
+ sigma: 0.0225
5
+ alpha: 0.0035
6
+ pop_size: 60
7
+ reward_normalization: zscore
8
+ schedule_mode: keep_tail_per_epoch
9
+ reward_normalization_ddof: 0
10
+ reward_normalization_eps: 1.0e-08
11
+ sync_engines_on_validate: false
12
+ sync_engine_reference: 0
13
+ raw_train_size: 7473
14
+ effective_train_size: 7473
15
+ max_steps: 750
16
+ config_version: 2
17
+ method: es
18
+ finetune:
19
+ type: lora
20
+ lora_rank: 16
21
+ lora_alpha: 16
22
+ target_modules:
23
+ - q_proj
24
+ - v_proj
25
+ method_params: {}
26
+ output:
27
+ seed: 42
28
+ dir: /home/zhi/ljq/ES4LLM/curves/lora/r16/20260528_151958_2862980/sigma0.0225_alpha0.0035
29
+ dtype: bfloat16
30
+ benchmark: gsm8k
31
+ gsm8k_path: /home/zhi/ES4LLM-main/data/dataset/gsm8k
32
+ checkpoint:
33
+ save_freq: 50
34
+ export_merged_freq: 50
35
+ generation:
36
+ max_new_tokens: 2048
37
+ format_reward: 0.1
38
+ model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
39
+ runtime:
40
+ model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
Qwen2.5-1.5B-R16-s0.0225-a0.0035/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c9f19dd3fd1acc5f93c42b00b3809ba192de1ae23bcc7557e987750db05a2c
3
+ size 99298
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c056f4a27d910748710a6cfb66061c3a2d36ca5b2ff0c7df9380cd17bf9e2d2b
3
+ size 1400
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a89c6041769f892fdc5bb02d964afd490f3f5f71baa695be57f909b55e8770b
3
+ size 3554214720
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
3
+ size 4686
Qwen2.5-1.5B-R16-s0.0225-a0.0035/merged/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833
Qwen2.5-1.5B-R16-s0.0225-a0.0035/tensorboard/events.out.tfevents.1779981759.sys-421gu-tnxr.2863018.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db1691fc31f5735c032f33b8d83ce31e3e0baeb239fba19d0be44b0fc4dcce0
3
+ size 126977
Qwen2.5-1.5B-R16-s0.0225-a0.005/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae47c569e707bff03a6e16175ad8a0de5890534189119809bff706f924e907d
3
+ size 99964
Qwen2.5-1.5B-R16-s0.0225-a0.005/merged ADDED
@@ -0,0 +1 @@
 
 
1
+ /home/zhi/ljq/ES4LLM/.runtime_storage/outputs/lora_checkpoint_archive/from_curves_lora/r16/20260527_160155_3547781/sigma0.0225_alpha0.005/Qwen2.5-1.5B-Instruct/sigma0.0225_alpha0.005_N60_ep10_s42_20260527_160205/merged
Qwen2.5-1.5B-R16-s0.0225-a0.005/tensorboard/events.out.tfevents.1779897887.sys-421gu-tnxr.3547822.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d09edbeaff3a34f2ec89b7077a3948a75a83c478fffc088685da830db89699
3
+ size 126975