Integrate with Sentence Transformers v5.4

#1
by tomaarsen HF Staff - opened
1_LogitScore/config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "true_token_id": 9693,
3
+ "false_token_id": 2152
4
+ }
chat_template.jinja CHANGED
@@ -1,85 +1,15 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# 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>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\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" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
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 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.role == "user") or (message.role == "system" and not loop.first) %}
27
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
- {%- elif message.role == "assistant" %}
29
- {%- set content = message.content %}
30
- {%- set reasoning_content = '' %}
31
- {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
- {%- set reasoning_content = message.reasoning_content %}
33
- {%- else %}
34
- {%- if '</think>' in message.content %}
35
- {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
- {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
- {%- endif %}
38
- {%- endif %}
39
- {%- if loop.index0 > ns.last_query_index %}
40
- {%- if loop.last or (not loop.last and reasoning_content) %}
41
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
- {%- else %}
43
- {{- '<|im_start|>' + message.role + '\n' + content }}
44
- {%- endif %}
45
- {%- else %}
46
- {{- '<|im_start|>' + message.role + '\n' + content }}
47
- {%- endif %}
48
- {%- if message.tool_calls %}
49
- {%- for tool_call in message.tool_calls %}
50
- {%- if (loop.first and content) or (not loop.first) %}
51
- {{- '\n' }}
52
- {%- endif %}
53
- {%- if tool_call.function %}
54
- {%- set tool_call = tool_call.function %}
55
- {%- endif %}
56
- {{- '<tool_call>\n{"name": "' }}
57
- {{- tool_call.name }}
58
- {{- '", "arguments": ' }}
59
- {%- if tool_call.arguments is string %}
60
- {{- tool_call.arguments }}
61
- {%- else %}
62
- {{- tool_call.arguments | tojson }}
63
- {%- endif %}
64
- {{- '}\n</tool_call>' }}
65
- {%- endfor %}
66
- {%- endif %}
67
- {{- '<|im_end|>\n' }}
68
- {%- elif message.role == "tool" %}
69
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
- {{- '<|im_start|>user' }}
71
- {%- endif %}
72
- {{- '\n<tool_response>\n' }}
73
- {{- message.content }}
74
- {{- '\n</tool_response>' }}
75
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
- {{- '<|im_end|>\n' }}
77
- {%- endif %}
78
- {%- endif %}
79
- {%- endfor %}
80
- {%- if add_generation_prompt %}
81
- {{- '<|im_start|>assistant\n' }}
82
- {%- if enable_thinking is defined and enable_thinking is false %}
83
- {{- '<think>\n\n</think>\n\n' }}
84
- {%- endif %}
85
- {%- endif %}
 
1
+ {%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a web search query, retrieve relevant passages that answer the query") -%}
2
+ {%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%}
3
+ {%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%}
4
+ <|im_start|>system
5
+ Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
6
+ <|im_start|>user
7
+ <Instruct>: {{ instruction }}
8
+ <Query>: {{ query_text }}
9
+ <Document>: {{ document_text }}<|im_end|>
10
+ <|im_start|>assistant
11
+ <think>
12
+
13
+ </think>
14
+
15
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config_sentence_transformers.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.10.0+cu128",
4
+ "sentence_transformers": "5.4.0"
5
+ },
6
+ "activation_fn": "torch.nn.modules.linear.Identity",
7
+ "default_prompt_name": "query",
8
+ "model_type": "CrossEncoder",
9
+ "prompts": {
10
+ "query": "Given a web search query, retrieve relevant passages that answer the query"
11
+ }
12
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_LogitScore",
12
+ "type": "sentence_transformers.cross_encoder.modules.logit_score.LogitScore"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "text-generation",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "logits"
7
+ },
8
+ "message": {
9
+ "method": "forward",
10
+ "method_output_name": "logits",
11
+ "format": "flat"
12
+ }
13
+ },
14
+ "module_output_name": "causal_logits"
15
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|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
+ }