victormaricato commited on
Commit
ff41722
·
verified ·
1 Parent(s): 1a5e81e

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - text-generation
6
  - peft
7
  library_name: transformers
8
- base_model: Qwen/Qwen3-32B
9
  widget:
10
  - messages:
11
  - role: user
 
5
  - text-generation
6
  - peft
7
  library_name: transformers
8
+ base_model: kiwikiw/Affine-0004
9
  widget:
10
  - messages:
11
  - role: user
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "Qwen/Qwen3-32B",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "gate_proj",
27
- "v_proj",
28
  "down_proj",
29
  "o_proj",
30
  "up_proj",
 
 
31
  "q_proj",
32
- "k_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "kiwikiw/Affine-0004",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "down_proj",
27
  "o_proj",
28
  "up_proj",
29
+ "v_proj",
30
+ "k_proj",
31
  "q_proj",
32
+ "gate_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca19564c513606ce7faaf6b034b59ad4926409c4a864a62d46e8b8c2216c102e
3
- size 3374740928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc51ba349e885753da4c4492438c7644a7f4e84cdc2a965c3da82451febd4a1
3
+ size 1685278680
chat_template.jinja CHANGED
@@ -14,14 +14,6 @@
14
  {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
  {%- endif %}
16
  {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
  {%- for message in messages %}
26
  {%- if message.content is string %}
27
  {%- set content = message.content %}
@@ -31,24 +23,7 @@
31
  {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
  {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
  {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
  {%- if message.tool_calls %}
53
  {%- for tool_call in message.tool_calls %}
54
  {%- if (loop.first and content) or (not loop.first) %}
@@ -83,7 +58,4 @@
83
  {%- endfor %}
84
  {%- if add_generation_prompt %}
85
  {{- '<|im_start|>assistant\n' }}
86
- {%- if enable_thinking is defined and enable_thinking is false %}
87
- {{- '<think>\n\n</think>\n\n' }}
88
- {%- endif %}
89
  {%- endif %}
 
14
  {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
  {%- endif %}
16
  {%- endif %}
 
 
 
 
 
 
 
 
17
  {%- for message in messages %}
18
  {%- if message.content is string %}
19
  {%- set content = message.content %}
 
23
  {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
  {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
  {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  {%- if message.tool_calls %}
28
  {%- for tool_call in message.tool_calls %}
29
  {%- if (loop.first and content) or (not loop.first) %}
 
58
  {%- endfor %}
59
  {%- if add_generation_prompt %}
60
  {{- '<|im_start|>assistant\n' }}
 
 
 
61
  {%- endif %}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4fa7a9bf893b173e25fce994cc61f8d4c3b3dcf0d369d45201814856449fec5
3
- size 6968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4393acc0417a3823ed1b318b2d9d0e250e7137c47b43349bd22cb9db57185bc5
3
+ size 5688
training_params.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "model": "Qwen/Qwen3-32B",
3
  "project_name": "syndra-medium",
4
  "data_path": "victormaricato/syndra-autotrain-dataset",
5
  "train_split": "train",
@@ -43,7 +43,7 @@
43
  "text_column": "output",
44
  "rejected_text_column": null,
45
  "push_to_hub": true,
46
- "username": "victormaricato",
47
  "unsloth": false,
48
- "distributed_backend": "deepspeed"
49
  }
 
1
  {
2
+ "model": "kiwikiw/Affine-0004",
3
  "project_name": "syndra-medium",
4
  "data_path": "victormaricato/syndra-autotrain-dataset",
5
  "train_split": "train",
 
43
  "text_column": "output",
44
  "rejected_text_column": null,
45
  "push_to_hub": true,
46
+ "username": "AgentGYM-exp",
47
  "unsloth": false,
48
+ "distributed_backend": null
49
  }