Add reverse-text SFT step_100 (hf_style_weights)
Browse files- chat_template.jinja +61 -26
- config.json +2 -1
- generation_config.json +10 -4
- pytorch_model.bin +1 -1
chat_template.jinja
CHANGED
@@ -1,48 +1,80 @@
|
|
1 |
{%- if tools %}
|
2 |
{{- '<|im_start|>system\n' }}
|
3 |
-
{%- if messages[0]
|
4 |
-
{{- messages[0]
|
5 |
-
{%- else %}
|
6 |
-
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
7 |
{%- endif %}
|
8 |
-
{{- "
|
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]
|
16 |
-
{{- '<|im_start|>system\n' + messages[0]
|
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
|
23 |
-
{
|
|
|
|
|
|
|
|
|
|
|
24 |
{%- elif message.role == "assistant" %}
|
25 |
-
{
|
26 |
-
{%- if message.
|
27 |
-
{
|
|
|
|
|
|
|
|
|
|
|
28 |
{%- endif %}
|
29 |
-
{%-
|
30 |
-
{%- if
|
31 |
-
{
|
|
|
|
|
32 |
{%- endif %}
|
33 |
-
|
34 |
-
{{-
|
35 |
-
|
36 |
-
|
37 |
-
{
|
38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
{{- '<|im_end|>\n' }}
|
40 |
{%- elif message.role == "tool" %}
|
41 |
-
{%- if
|
42 |
{{- '<|im_start|>user' }}
|
43 |
{%- endif %}
|
44 |
{{- '\n<tool_response>\n' }}
|
45 |
-
{{-
|
46 |
{{- '\n</tool_response>' }}
|
47 |
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
48 |
{{- '<|im_end|>\n' }}
|
@@ -51,4 +83,7 @@
|
|
51 |
{%- endfor %}
|
52 |
{%- if add_generation_prompt %}
|
53 |
{{- '<|im_start|>assistant\n' }}
|
54 |
-
{%-
|
|
|
|
|
|
|
|
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 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 %}
|
28 |
+
{%- else %}
|
29 |
+
{%- set content = '' %}
|
30 |
+
{%- endif %}
|
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) %}
|
55 |
+
{{- '\n' }}
|
56 |
+
{%- endif %}
|
57 |
+
{%- if tool_call.function %}
|
58 |
+
{%- set tool_call = tool_call.function %}
|
59 |
+
{%- endif %}
|
60 |
+
{{- '<tool_call>\n{"name": "' }}
|
61 |
+
{{- tool_call.name }}
|
62 |
+
{{- '", "arguments": ' }}
|
63 |
+
{%- if tool_call.arguments is string %}
|
64 |
+
{{- tool_call.arguments }}
|
65 |
+
{%- else %}
|
66 |
+
{{- tool_call.arguments | tojson }}
|
67 |
+
{%- endif %}
|
68 |
+
{{- '}\n</tool_call>' }}
|
69 |
+
{%- endfor %}
|
70 |
+
{%- endif %}
|
71 |
{{- '<|im_end|>\n' }}
|
72 |
{%- elif message.role == "tool" %}
|
73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
74 |
{{- '<|im_start|>user' }}
|
75 |
{%- endif %}
|
76 |
{{- '\n<tool_response>\n' }}
|
77 |
+
{{- content }}
|
78 |
{{- '\n</tool_response>' }}
|
79 |
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
80 |
{{- '<|im_end|>\n' }}
|
|
|
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 %}
|
config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 151643,
|
8 |
-
"dtype": "
|
9 |
"eos_token_id": 151645,
|
10 |
"head_dim": 128,
|
11 |
"hidden_act": "silu",
|
@@ -55,6 +55,7 @@
|
|
55 |
"tie_word_embeddings": true,
|
56 |
"transformers_version": "4.56.1",
|
57 |
"use_cache": false,
|
|
|
58 |
"use_sliding_window": false,
|
59 |
"vocab_size": 151936
|
60 |
}
|
|
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 151643,
|
8 |
+
"dtype": "bfloat16",
|
9 |
"eos_token_id": 151645,
|
10 |
"head_dim": 128,
|
11 |
"hidden_act": "silu",
|
|
|
55 |
"tie_word_embeddings": true,
|
56 |
"transformers_version": "4.56.1",
|
57 |
"use_cache": false,
|
58 |
+
"use_grouped_mm": true,
|
59 |
"use_sliding_window": false,
|
60 |
"vocab_size": 151936
|
61 |
}
|
generation_config.json
CHANGED
@@ -1,7 +1,13 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
"bos_token_id": 151643,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_k": 20,
|
11 |
+
"top_p": 0.95,
|
12 |
+
"transformers_version": "4.56.1"
|
13 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1503365567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:247ea4dbe16af994325fed2592fd8fb057285dccca67a7108678d5419f9a5bae
|
3 |
size 1503365567
|