Hugging Face's logo

ATL-Machine
/
affine-test-03

Safetensors
qwen3
Model card Files
xet
 Community
ATL-Machine commited on
Commit
4f4993b
·
verified ·
1 Parent(s): acae145

Upload model (bfloat16) from script

Browse files
Files changed (7) hide show
  1. chat_template.jinja +27 -32
  2. config.json +69 -67
  3. model-00001-of-00002.safetensors +2 -2
  4. model-00002-of-00002.safetensors +2 -2
  5. model.safetensors.index.json +0 -1
  6. tokenizer.json +2 -2
  7. tokenizer_config.json +4 -8
chat_template.jinja CHANGED
@@ -14,6 +14,14 @@
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 %}
@@ -23,13 +31,24 @@
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
-
27
- {%- set has_loss = (message.loss is defined and message.loss) %}
28
-
29
- {{- '<|im_start|>' + message.role + '\n' }}
30
- {%- if has_loss -%}
31
- {%- generation -%}
32
- {{- content }}
 
 
 
 
 
 
 
 
 
 
 
33
  {%- if message.tool_calls %}
34
  {%- for tool_call in message.tool_calls %}
35
  {%- if (loop.first and content) or (not loop.first) %}
@@ -50,30 +69,6 @@
50
  {%- endfor %}
51
  {%- endif %}
52
  {{- '<|im_end|>\n' }}
53
- {%- endgeneration -%}
54
- {%- else -%}
55
- {{- content }}
56
- {%- if message.tool_calls %}
57
- {%- for tool_call in message.tool_calls %}
58
- {%- if (loop.first and content) or (not loop.first) %}
59
- {{- '\n' }}
60
- {%- endif %}
61
- {%- if tool_call.function %}
62
- {%- set tool_call = tool_call.function %}
63
- {%- endif %}
64
- {{- '<tool_call>\n{"name": "' }}
65
- {{- tool_call.name }}
66
- {{- '", "arguments": ' }}
67
- {%- if tool_call.arguments is string %}
68
- {{- tool_call.arguments }}
69
- {%- else %}
70
- {{- tool_call.arguments | tojson }}
71
- {%- endif %}
72
- {{- '}\n</tool_call>' }}
73
- {%- endfor %}
74
- {%- endif %}
75
- {{- '<|im_end|>\n' }}
76
- {%- endif %}
77
  {%- elif message.role == "tool" %}
78
  {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
79
  {{- '<|im_start|>user' }}
@@ -87,5 +82,5 @@
87
  {%- endif %}
88
  {%- endfor %}
89
  {%- if add_generation_prompt %}
90
- {{- '<|im_start|>assistant\n' }}
91
  {%- endif %}
 
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
  {%- 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) %}
 
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' }}
 
82
  {%- endif %}
83
  {%- endfor %}
84
  {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n<think>\n' }}
86
  {%- endif %}
config.json CHANGED
@@ -1,68 +1,70 @@
1
  {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "layer_types": [
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
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention"
51
- ],
52
- "max_position_embeddings": 262144,
53
- "max_window_layers": 36,
54
- "model_type": "qwen3",
55
- "num_attention_heads": 32,
56
- "num_hidden_layers": 36,
57
- "num_key_value_heads": 8,
58
- "pad_token_id": 151643,
59
- "rms_norm_eps": 1e-06,
60
- "rope_scaling": null,
61
- "rope_theta": 5000000,
62
- "sliding_window": null,
63
- "tie_word_embeddings": true,
64
- "transformers_version": "4.57.3",
65
- "use_cache": false,
66
- "use_sliding_window": false,
67
- "vocab_size": 151936
68
- }
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "torch_dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
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
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 40960,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151643,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.6",
65
+ "unsloth_fixed": true,
66
+ "unsloth_version": "2026.1.2",
67
+ "use_cache": true,
68
+ "use_sliding_window": false,
69
+ "vocab_size": 151936
70
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fa19648adbf9ec8871972abd8aadde368c81ead81a781495f562c6b11e35fbc
3
- size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e803df884994f5d632dd4ef02b39c3cae2c69270bcf1ebe9ae8b395cc4944e49
3
+ size 4967215455
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d65c7787e80724cc5b58cfdf5845e2c02de90d3db2c3a17be1efca77cd877244
3
- size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c9c5e2dde001617c0ad2f8cb233de2a13427b87af6f01dd570bc93d67b2f99
3
+ size 3077766730
model.safetensors.index.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
  "metadata": {
3
- "total_parameters": 4022468096,
4
  "total_size": 8044936192
5
  },
6
  "weight_map": {
 
1
  {
2
  "metadata": {
 
3
  "total_size": 8044936192
4
  },
5
  "weight_map": {
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8099b060b1326ce3e9d0e5ab5b8c1651279edb15ad6e52059f082c3a885c416
3
- size 11422753
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json CHANGED
@@ -231,14 +231,10 @@
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
  "extra_special_tokens": {},
234
- "max_length": 3720,
235
- "model_max_length": 1010000,
236
  "pad_token": "<|endoftext|>",
237
- "padding_side": "right",
238
  "split_special_tokens": false,
239
- "stride": 0,
240
  "tokenizer_class": "Qwen2Tokenizer",
241
- "truncation_side": "right",
242
- "truncation_strategy": "longest_first",
243
- "unk_token": null
244
- }
 
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
  "extra_special_tokens": {},
234
+ "model_max_length": 131072,
 
235
  "pad_token": "<|endoftext|>",
 
236
  "split_special_tokens": false,
 
237
  "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null,
239
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- 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>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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<think>\\n' }}\n{%- endif %}"
240
+ }