ljq34952 commited on
Commit
19f93b2
·
verified ·
1 Parent(s): ab5139f

Add files using upload-large-folder tool

Browse files
Files changed (36) hide show
  1. Qwen2.5-1.5B-R4-s0.02-a0.005/config.yaml +43 -0
  2. Qwen2.5-1.5B-R4-s0.02-a0.005/history.json +3 -0
  3. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/added_tokens.json +3 -0
  4. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/chat_template.jinja +54 -0
  5. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/config.json +3 -0
  6. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/merges.txt +0 -0
  7. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/model.safetensors +3 -0
  8. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/special_tokens_map.json +3 -0
  9. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/tokenizer.json +3 -0
  10. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/tokenizer_config.json +3 -0
  11. Qwen2.5-1.5B-R4-s0.02-a0.005/merged/vocab.json +3 -0
  12. Qwen2.5-1.5B-R4-s0.02-a0.005/tensorboard/events.out.tfevents.1779636171.liu-SGASL90-002.97073.0 +3 -0
  13. Qwen2.5-1.5B-R4-s0.02-a0.0075/config.yaml +43 -0
  14. Qwen2.5-1.5B-R4-s0.02-a0.0075/history.json +3 -0
  15. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/added_tokens.json +3 -0
  16. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/chat_template.jinja +54 -0
  17. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/config.json +3 -0
  18. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/merges.txt +0 -0
  19. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/model.safetensors +3 -0
  20. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/special_tokens_map.json +3 -0
  21. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/tokenizer.json +3 -0
  22. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/tokenizer_config.json +3 -0
  23. Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/vocab.json +3 -0
  24. Qwen2.5-1.5B-R4-s0.02-a0.0075/tensorboard/events.out.tfevents.1779636170.liu-SGASL90-002.97201.0 +3 -0
  25. Qwen2.5-1.5B-R4-s0.0225-a0.0025/config.yaml +43 -0
  26. Qwen2.5-1.5B-R4-s0.0225-a0.0025/history.json +3 -0
  27. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/added_tokens.json +3 -0
  28. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/chat_template.jinja +54 -0
  29. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/config.json +3 -0
  30. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/merges.txt +0 -0
  31. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/model.safetensors +3 -0
  32. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/special_tokens_map.json +3 -0
  33. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/tokenizer.json +3 -0
  34. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/tokenizer_config.json +3 -0
  35. Qwen2.5-1.5B-R4-s0.0225-a0.0025/merged/vocab.json +3 -0
  36. Qwen2.5-1.5B-R4-s0.0225-a0.0025/tensorboard/events.out.tfevents.1779636170.liu-SGASL90-002.97074.0 +3 -0
Qwen2.5-1.5B-R4-s0.02-a0.005/config.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ es:
2
+ n_epochs: 10
3
+ batch_size: 100
4
+ sigma: 0.02
5
+ alpha: 0.005
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
+ raw_train_size: 7473
12
+ effective_train_size: 7473
13
+ max_steps: 750
14
+ config_version: 2
15
+ method: es
16
+ finetune:
17
+ type: lora
18
+ lora_rank: 4
19
+ lora_alpha: 4
20
+ target_modules:
21
+ - q_proj
22
+ - k_proj
23
+ - v_proj
24
+ - o_proj
25
+ - gate_proj
26
+ - up_proj
27
+ - down_proj
28
+ method_params: {}
29
+ output:
30
+ seed: 42
31
+ dir: /home/bayp/ljq/ES4LLM/curves/lora/r4/20260524_232114_97023/sigma0.02_alpha0.005
32
+ dtype: bfloat16
33
+ benchmark: gsm8k
34
+ gsm8k_path: /home/bayp/EsSftSVD/data/dataset/gsm8k
35
+ checkpoint:
36
+ save_freq: 50
37
+ export_merged_freq: 50
38
+ generation:
39
+ max_new_tokens: 2048
40
+ format_reward: 0.1
41
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
42
+ runtime:
43
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
Qwen2.5-1.5B-R4-s0.02-a0.005/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac400a67509dc5dce973e0979fa8a6a77313b228b0343a8e983ff95c05488beb
3
+ size 99580
Qwen2.5-1.5B-R4-s0.02-a0.005/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-R4-s0.02-a0.005/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-R4-s0.02-a0.005/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-R4-s0.02-a0.005/merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-R4-s0.02-a0.005/merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394a5817d92e0a36a20ff7cc84777c1ec03f20264ef9a7c5e2b37330035130e9
3
+ size 3554214720
Qwen2.5-1.5B-R4-s0.02-a0.005/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-R4-s0.02-a0.005/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-R4-s0.02-a0.005/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-R4-s0.02-a0.005/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-R4-s0.02-a0.005/tensorboard/events.out.tfevents.1779636171.liu-SGASL90-002.97073.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce1a9219defbdbe1d152613cdd2917c9f7c7098b6e7c93e17ee561ed97ca3d5
3
+ size 127001
Qwen2.5-1.5B-R4-s0.02-a0.0075/config.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ es:
2
+ n_epochs: 10
3
+ batch_size: 100
4
+ sigma: 0.02
5
+ alpha: 0.0075
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
+ raw_train_size: 7473
12
+ effective_train_size: 7473
13
+ max_steps: 750
14
+ config_version: 2
15
+ method: es
16
+ finetune:
17
+ type: lora
18
+ lora_rank: 4
19
+ lora_alpha: 4
20
+ target_modules:
21
+ - q_proj
22
+ - k_proj
23
+ - v_proj
24
+ - o_proj
25
+ - gate_proj
26
+ - up_proj
27
+ - down_proj
28
+ method_params: {}
29
+ output:
30
+ seed: 42
31
+ dir: /home/bayp/ljq/ES4LLM/curves/lora/r4/20260524_232114_97023/sigma0.02_alpha0.0075
32
+ dtype: bfloat16
33
+ benchmark: gsm8k
34
+ gsm8k_path: /home/bayp/EsSftSVD/data/dataset/gsm8k
35
+ checkpoint:
36
+ save_freq: 50
37
+ export_merged_freq: 50
38
+ generation:
39
+ max_new_tokens: 2048
40
+ format_reward: 0.1
41
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
42
+ runtime:
43
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
Qwen2.5-1.5B-R4-s0.02-a0.0075/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646d74a0c2c1849bb6087d20d35e8f5ff8ef38155ac58e039b3e30b6094e61e9
3
+ size 100518
Qwen2.5-1.5B-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-R4-s0.02-a0.0075/merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2abc43c4471c62f856c253851687474138b4cc43b1ff8888579563e1b7353a
3
+ size 3554214720
Qwen2.5-1.5B-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/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-R4-s0.02-a0.0075/tensorboard/events.out.tfevents.1779636170.liu-SGASL90-002.97201.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10505ff13a4fe4352a5e4fae5c8d2717717ffc8b9cd8c83bcea721536487d8d4
3
+ size 127003
Qwen2.5-1.5B-R4-s0.0225-a0.0025/config.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ raw_train_size: 7473
12
+ effective_train_size: 7473
13
+ max_steps: 750
14
+ config_version: 2
15
+ method: es
16
+ finetune:
17
+ type: lora
18
+ lora_rank: 4
19
+ lora_alpha: 4
20
+ target_modules:
21
+ - q_proj
22
+ - k_proj
23
+ - v_proj
24
+ - o_proj
25
+ - gate_proj
26
+ - up_proj
27
+ - down_proj
28
+ method_params: {}
29
+ output:
30
+ seed: 42
31
+ dir: /home/bayp/ljq/ES4LLM/curves/lora/r4/20260524_232114_97023/sigma0.0225_alpha0.0025
32
+ dtype: bfloat16
33
+ benchmark: gsm8k
34
+ gsm8k_path: /home/bayp/EsSftSVD/data/dataset/gsm8k
35
+ checkpoint:
36
+ save_freq: 50
37
+ export_merged_freq: 50
38
+ generation:
39
+ max_new_tokens: 2048
40
+ format_reward: 0.1
41
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
42
+ runtime:
43
+ model: /home/bayp/EsSftSVD/data/model/Qwen2.5-1.5B-Instruct
Qwen2.5-1.5B-R4-s0.0225-a0.0025/history.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6952f9b3ac6b5601827147deee7bfb6672647de3e76c3c14887d72c3d09b2f9c
3
+ size 100091
Qwen2.5-1.5B-R4-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-R4-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-R4-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-R4-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-R4-s0.0225-a0.0025/merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f452f82728cc008437aa7bda97d41cb3071a3a12574b31cbc1eaa245331db6c9
3
+ size 3554214720
Qwen2.5-1.5B-R4-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-R4-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-R4-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-R4-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-R4-s0.0225-a0.0025/tensorboard/events.out.tfevents.1779636170.liu-SGASL90-002.97074.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7736241a34fc308974f74c2b205c242680f4ec38931ac8d49056cd538fac8292
3
+ size 127007