Training in progress, step 160
Browse files- chat_template.jinja +54 -0
- config.json +32 -2
- model.safetensors +1 -1
- tokenizer_config.json +0 -1
- training_args.bin +1 -1
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 %}
|
config.json
CHANGED
@@ -9,6 +9,36 @@
|
|
9 |
"hidden_size": 1536,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 8960,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 21,
|
14 |
"model_type": "qwen2",
|
@@ -18,10 +48,10 @@
|
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_scaling": null,
|
20 |
"rope_theta": 1000000.0,
|
21 |
-
"sliding_window":
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": false,
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
|
|
9 |
"hidden_size": 1536,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 8960,
|
12 |
+
"layer_types": [
|
13 |
+
"full_attention",
|
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 |
+
],
|
42 |
"max_position_embeddings": 32768,
|
43 |
"max_window_layers": 21,
|
44 |
"model_type": "qwen2",
|
|
|
48 |
"rms_norm_eps": 1e-06,
|
49 |
"rope_scaling": null,
|
50 |
"rope_theta": 1000000.0,
|
51 |
+
"sliding_window": null,
|
52 |
"tie_word_embeddings": true,
|
53 |
"torch_dtype": "bfloat16",
|
54 |
+
"transformers_version": "4.53.0",
|
55 |
"use_cache": false,
|
56 |
"use_sliding_window": false,
|
57 |
"vocab_size": 151936
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3554214752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1b2ac732ed22d788b6249bf22d1370d7f2ca21f89ac8f8b3e1d4214bd1c9db7
|
3 |
size 3554214752
|
tokenizer_config.json
CHANGED
@@ -195,7 +195,6 @@
|
|
195 |
"<|video_pad|>"
|
196 |
],
|
197 |
"bos_token": null,
|
198 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
|
|
195 |
"<|video_pad|>"
|
196 |
],
|
197 |
"bos_token": null,
|
|
|
198 |
"clean_up_tokenization_spaces": false,
|
199 |
"eos_token": "<|im_end|>",
|
200 |
"errors": "replace",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e3b56ff1929aae05c6c35e6c228546360922b24f9cc4ee62d5faa3a46391deb
|
3 |
size 8312
|