Hugging Face's logo

mahernaija
/
Qwen3.5-27B-Text2SQL

Text Generation
Safetensors
English
qwen3_5
text-to-sql
sql
qwen3.5
fine-tuned
fsdp
nebius
conversational
Model card Files
xet
 Community
mahernaija commited on
Commit
5e81299
·
verified ·
1 Parent(s): f7045ff

Upload folder using huggingface_hub

Browse files
Files changed (44) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +154 -0
  3. checkpoint-698/chat_template.jinja +154 -0
  4. checkpoint-698/config.json +115 -0
  5. checkpoint-698/generation_config.json +13 -0
  6. checkpoint-698/model-00001-of-00003.safetensors +3 -0
  7. checkpoint-698/model-00002-of-00003.safetensors +3 -0
  8. checkpoint-698/model-00003-of-00003.safetensors +3 -0
  9. checkpoint-698/model.safetensors.index.json +859 -0
  10. checkpoint-698/optimizer.bin +3 -0
  11. checkpoint-698/pytorch_model_fsdp.bin +3 -0
  12. checkpoint-698/rng_state_0.pth +3 -0
  13. checkpoint-698/rng_state_1.pth +3 -0
  14. checkpoint-698/rng_state_10.pth +3 -0
  15. checkpoint-698/rng_state_11.pth +3 -0
  16. checkpoint-698/rng_state_12.pth +3 -0
  17. checkpoint-698/rng_state_13.pth +3 -0
  18. checkpoint-698/rng_state_14.pth +3 -0
  19. checkpoint-698/rng_state_15.pth +3 -0
  20. checkpoint-698/rng_state_2.pth +3 -0
  21. checkpoint-698/rng_state_3.pth +3 -0
  22. checkpoint-698/rng_state_4.pth +3 -0
  23. checkpoint-698/rng_state_5.pth +3 -0
  24. checkpoint-698/rng_state_6.pth +3 -0
  25. checkpoint-698/rng_state_7.pth +3 -0
  26. checkpoint-698/rng_state_8.pth +3 -0
  27. checkpoint-698/rng_state_9.pth +3 -0
  28. checkpoint-698/scheduler.pt +3 -0
  29. checkpoint-698/tokenizer.json +3 -0
  30. checkpoint-698/tokenizer_config.json +31 -0
  31. checkpoint-698/trainer_state.json +556 -0
  32. checkpoint-698/training_args.bin +3 -0
  33. config.json +135 -0
  34. generation_config.json +13 -0
  35. merges.txt +0 -0
  36. model-00001-of-00003.safetensors +3 -0
  37. model-00002-of-00003.safetensors +3 -0
  38. model-00003-of-00003.safetensors +3 -0
  39. model-visual.safetensors +3 -0
  40. model.safetensors.index.json +0 -0
  41. preprocessor_config.json +21 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +305 -0
  44. video_preprocessor_config.json +21 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-698/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
checkpoint-698/chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
checkpoint-698/config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_output_gate": true,
8
+ "bos_token_id": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 248046,
11
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 17408,
17
+ "layer_types": [
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention"
82
+ ],
83
+ "linear_conv_kernel_dim": 4,
84
+ "linear_key_head_dim": 128,
85
+ "linear_num_key_heads": 16,
86
+ "linear_num_value_heads": 48,
87
+ "linear_value_head_dim": 128,
88
+ "mamba_ssm_dtype": "float32",
89
+ "max_position_embeddings": 262144,
90
+ "mlp_only_layers": [],
91
+ "model_type": "qwen3_5_text",
92
+ "mtp_num_hidden_layers": 1,
93
+ "mtp_use_dedicated_embeddings": false,
94
+ "num_attention_heads": 24,
95
+ "num_hidden_layers": 64,
96
+ "num_key_value_heads": 4,
97
+ "pad_token_id": 248044,
98
+ "partial_rotary_factor": 0.25,
99
+ "rms_norm_eps": 1e-06,
100
+ "rope_parameters": {
101
+ "mrope_interleaved": true,
102
+ "mrope_section": [
103
+ 11,
104
+ 11,
105
+ 10
106
+ ],
107
+ "partial_rotary_factor": 0.25,
108
+ "rope_theta": 10000000,
109
+ "rope_type": "default"
110
+ },
111
+ "tie_word_embeddings": false,
112
+ "transformers_version": "5.5.0.dev0",
113
+ "use_cache": false,
114
+ "vocab_size": 248320
115
+ }
checkpoint-698/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.5.0.dev0"
13
+ }
checkpoint-698/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f64b9eb55249a390f634753d9fd3a1d4902214dfa384b3275278968a268865
3
+ size 49979080424
checkpoint-698/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840952a248fdcb13de4834428baf32b82e53d9572ffbfd26cc3b17d3ae906773
3
+ size 49671140304
checkpoint-698/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30e39f7a3d9dde91061a883c9d1c35045772937c3e17e1372b665c933940a77
3
+ size 7933885616
checkpoint-698/model.safetensors.index.json ADDED
@@ -0,0 +1,859 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1680999904,
4
+ "total_size": 107583993856
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00003.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
+ "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00003.safetensors",
11
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
12
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
16
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
17
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
18
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
23
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00003.safetensors",
25
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
26
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
27
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
28
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
29
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
30
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
31
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
32
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
37
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
38
+ "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00003.safetensors",
39
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
40
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
41
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
42
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
43
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
44
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
45
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
46
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
51
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
52
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
54
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
56
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
57
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
60
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
63
+ "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00003.safetensors",
64
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
65
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
66
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
67
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
68
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
69
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
70
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
71
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
72
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
75
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
76
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
77
+ "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00003.safetensors",
78
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
79
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
80
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
81
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
82
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
83
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
84
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
85
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
86
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
87
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
89
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
90
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
91
+ "model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00003.safetensors",
92
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
93
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
94
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
95
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
96
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
97
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
98
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
99
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
100
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
102
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
103
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
104
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
105
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
106
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
107
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
109
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
110
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
111
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
112
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
113
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
114
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
115
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
116
+ "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00003.safetensors",
117
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
118
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
119
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
120
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
121
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
122
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
123
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
124
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
126
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
127
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
128
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
129
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
130
+ "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00003.safetensors",
131
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
132
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
133
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
134
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
135
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
136
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
137
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
138
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
139
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
140
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
141
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
142
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
143
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
144
+ "model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00003.safetensors",
145
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
146
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
147
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
148
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
149
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
150
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
151
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
152
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
153
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
154
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
155
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
156
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
157
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
158
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
159
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
160
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
161
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
162
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
163
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
164
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
165
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
166
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
167
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
168
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
169
+ "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00003.safetensors",
170
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
171
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
172
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
173
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
174
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
175
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
176
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
177
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
178
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
179
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
180
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
181
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
182
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
183
+ "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00003.safetensors",
184
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
185
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
186
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
187
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
188
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
189
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
190
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
191
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
192
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
193
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
194
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
195
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
196
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00003.safetensors",
198
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
199
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
200
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
201
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
202
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
203
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
204
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
205
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
210
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
211
+ "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00003.safetensors",
212
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
213
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
214
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
215
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
216
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
217
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
218
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
219
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors",
225
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
229
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
230
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
233
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
236
+ "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00003.safetensors",
237
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
238
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
239
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
240
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
241
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
242
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
243
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
244
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
249
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
250
+ "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00003.safetensors",
251
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
252
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
253
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
254
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
255
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
256
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
257
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
258
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
261
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
263
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
264
+ "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00003.safetensors",
265
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
266
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
267
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
268
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
269
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
270
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
271
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
272
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
274
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
276
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
277
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
278
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
281
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
282
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
283
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
285
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
286
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
288
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
289
+ "model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00003.safetensors",
290
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
291
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
292
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
293
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
294
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
295
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
296
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
297
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
298
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
299
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
300
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
302
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
303
+ "model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00003.safetensors",
304
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
305
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
306
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
307
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
308
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
309
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
310
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
311
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
313
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
314
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
316
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
317
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
319
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
321
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
322
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
323
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
324
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
325
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
328
+ "model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00003.safetensors",
329
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
330
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
331
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
332
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
333
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
334
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
335
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
336
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
337
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
339
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
340
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
341
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
342
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
344
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
345
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
346
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
347
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
348
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
349
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
350
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
351
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
352
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
353
+ "model.language_model.layers.32.linear_attn.A_log": "model-00002-of-00003.safetensors",
354
+ "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
355
+ "model.language_model.layers.32.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
356
+ "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
357
+ "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
358
+ "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
359
+ "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
360
+ "model.language_model.layers.32.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
361
+ "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
362
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
363
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
364
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
365
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
366
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
367
+ "model.language_model.layers.33.linear_attn.A_log": "model-00002-of-00003.safetensors",
368
+ "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
369
+ "model.language_model.layers.33.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
370
+ "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
371
+ "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
372
+ "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
373
+ "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
374
+ "model.language_model.layers.33.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
375
+ "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
376
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
377
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
378
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
379
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
380
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
381
+ "model.language_model.layers.34.linear_attn.A_log": "model-00002-of-00003.safetensors",
382
+ "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
383
+ "model.language_model.layers.34.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
384
+ "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
385
+ "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
386
+ "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
387
+ "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
388
+ "model.language_model.layers.34.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
389
+ "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
390
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
391
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
392
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
393
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
394
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
395
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
396
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
397
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
398
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
399
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
400
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
401
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
402
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
403
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
404
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
405
+ "model.language_model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
406
+ "model.language_model.layers.36.linear_attn.A_log": "model-00002-of-00003.safetensors",
407
+ "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
408
+ "model.language_model.layers.36.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
409
+ "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
410
+ "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
411
+ "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
412
+ "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
413
+ "model.language_model.layers.36.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
414
+ "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
415
+ "model.language_model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
416
+ "model.language_model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
417
+ "model.language_model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
418
+ "model.language_model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
419
+ "model.language_model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
420
+ "model.language_model.layers.37.linear_attn.A_log": "model-00002-of-00003.safetensors",
421
+ "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
422
+ "model.language_model.layers.37.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
423
+ "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
424
+ "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
425
+ "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
426
+ "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
427
+ "model.language_model.layers.37.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
428
+ "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
429
+ "model.language_model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
430
+ "model.language_model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
431
+ "model.language_model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
432
+ "model.language_model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
433
+ "model.language_model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
434
+ "model.language_model.layers.38.linear_attn.A_log": "model-00002-of-00003.safetensors",
435
+ "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
436
+ "model.language_model.layers.38.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
437
+ "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
438
+ "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
439
+ "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
440
+ "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
441
+ "model.language_model.layers.38.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
442
+ "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
443
+ "model.language_model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
444
+ "model.language_model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
445
+ "model.language_model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
446
+ "model.language_model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
447
+ "model.language_model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
448
+ "model.language_model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
449
+ "model.language_model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
450
+ "model.language_model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
451
+ "model.language_model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
452
+ "model.language_model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
453
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
454
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
455
+ "model.language_model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
456
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
457
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
459
+ "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00003.safetensors",
460
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
461
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
462
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
463
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
464
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
465
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
466
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
467
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
468
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
469
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
470
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
471
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
472
+ "model.language_model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
473
+ "model.language_model.layers.40.linear_attn.A_log": "model-00002-of-00003.safetensors",
474
+ "model.language_model.layers.40.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
475
+ "model.language_model.layers.40.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
476
+ "model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
477
+ "model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
478
+ "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
479
+ "model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
480
+ "model.language_model.layers.40.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
481
+ "model.language_model.layers.40.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
482
+ "model.language_model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
483
+ "model.language_model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
484
+ "model.language_model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
485
+ "model.language_model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
486
+ "model.language_model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
487
+ "model.language_model.layers.41.linear_attn.A_log": "model-00002-of-00003.safetensors",
488
+ "model.language_model.layers.41.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
489
+ "model.language_model.layers.41.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
490
+ "model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
491
+ "model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
492
+ "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
493
+ "model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
494
+ "model.language_model.layers.41.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
495
+ "model.language_model.layers.41.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
496
+ "model.language_model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
497
+ "model.language_model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
498
+ "model.language_model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
499
+ "model.language_model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
500
+ "model.language_model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
501
+ "model.language_model.layers.42.linear_attn.A_log": "model-00002-of-00003.safetensors",
502
+ "model.language_model.layers.42.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
503
+ "model.language_model.layers.42.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
504
+ "model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
505
+ "model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
506
+ "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
507
+ "model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
508
+ "model.language_model.layers.42.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
509
+ "model.language_model.layers.42.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
510
+ "model.language_model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
511
+ "model.language_model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
512
+ "model.language_model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
513
+ "model.language_model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
514
+ "model.language_model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
515
+ "model.language_model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
516
+ "model.language_model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
517
+ "model.language_model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
518
+ "model.language_model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
519
+ "model.language_model.layers.43.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
520
+ "model.language_model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
521
+ "model.language_model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
522
+ "model.language_model.layers.43.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
523
+ "model.language_model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
524
+ "model.language_model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
525
+ "model.language_model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
526
+ "model.language_model.layers.44.linear_attn.A_log": "model-00002-of-00003.safetensors",
527
+ "model.language_model.layers.44.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
528
+ "model.language_model.layers.44.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
529
+ "model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
530
+ "model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
531
+ "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
532
+ "model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
533
+ "model.language_model.layers.44.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
534
+ "model.language_model.layers.44.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
535
+ "model.language_model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
536
+ "model.language_model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
537
+ "model.language_model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
538
+ "model.language_model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
539
+ "model.language_model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
540
+ "model.language_model.layers.45.linear_attn.A_log": "model-00002-of-00003.safetensors",
541
+ "model.language_model.layers.45.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
542
+ "model.language_model.layers.45.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
543
+ "model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
544
+ "model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
545
+ "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
546
+ "model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
547
+ "model.language_model.layers.45.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
548
+ "model.language_model.layers.45.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
549
+ "model.language_model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
550
+ "model.language_model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
551
+ "model.language_model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
552
+ "model.language_model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
553
+ "model.language_model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
554
+ "model.language_model.layers.46.linear_attn.A_log": "model-00002-of-00003.safetensors",
555
+ "model.language_model.layers.46.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
556
+ "model.language_model.layers.46.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
557
+ "model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
558
+ "model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
559
+ "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
560
+ "model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
561
+ "model.language_model.layers.46.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
562
+ "model.language_model.layers.46.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
563
+ "model.language_model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
564
+ "model.language_model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
565
+ "model.language_model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
566
+ "model.language_model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
567
+ "model.language_model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
568
+ "model.language_model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
569
+ "model.language_model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
570
+ "model.language_model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
571
+ "model.language_model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
572
+ "model.language_model.layers.47.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
573
+ "model.language_model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
574
+ "model.language_model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
575
+ "model.language_model.layers.47.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
576
+ "model.language_model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
577
+ "model.language_model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
578
+ "model.language_model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
579
+ "model.language_model.layers.48.linear_attn.A_log": "model-00002-of-00003.safetensors",
580
+ "model.language_model.layers.48.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
581
+ "model.language_model.layers.48.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
582
+ "model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
583
+ "model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
584
+ "model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
585
+ "model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
586
+ "model.language_model.layers.48.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
587
+ "model.language_model.layers.48.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
588
+ "model.language_model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
589
+ "model.language_model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
590
+ "model.language_model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
591
+ "model.language_model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
592
+ "model.language_model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors",
593
+ "model.language_model.layers.49.linear_attn.A_log": "model-00002-of-00003.safetensors",
594
+ "model.language_model.layers.49.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
595
+ "model.language_model.layers.49.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
596
+ "model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
597
+ "model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
598
+ "model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
599
+ "model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
600
+ "model.language_model.layers.49.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
601
+ "model.language_model.layers.49.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
602
+ "model.language_model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
603
+ "model.language_model.layers.49.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
604
+ "model.language_model.layers.49.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
605
+ "model.language_model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
606
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
607
+ "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00003.safetensors",
608
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
609
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
610
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
611
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
612
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
613
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
614
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
615
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
616
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
617
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
618
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
619
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
620
+ "model.language_model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors",
621
+ "model.language_model.layers.50.linear_attn.A_log": "model-00002-of-00003.safetensors",
622
+ "model.language_model.layers.50.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
623
+ "model.language_model.layers.50.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
624
+ "model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
625
+ "model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
626
+ "model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
627
+ "model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
628
+ "model.language_model.layers.50.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
629
+ "model.language_model.layers.50.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
630
+ "model.language_model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
631
+ "model.language_model.layers.50.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
632
+ "model.language_model.layers.50.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
633
+ "model.language_model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
634
+ "model.language_model.layers.51.input_layernorm.weight": "model-00002-of-00003.safetensors",
635
+ "model.language_model.layers.51.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
636
+ "model.language_model.layers.51.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
637
+ "model.language_model.layers.51.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
638
+ "model.language_model.layers.51.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
639
+ "model.language_model.layers.51.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
640
+ "model.language_model.layers.51.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
641
+ "model.language_model.layers.51.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
642
+ "model.language_model.layers.51.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
643
+ "model.language_model.layers.51.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
644
+ "model.language_model.layers.51.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
645
+ "model.language_model.layers.52.input_layernorm.weight": "model-00002-of-00003.safetensors",
646
+ "model.language_model.layers.52.linear_attn.A_log": "model-00002-of-00003.safetensors",
647
+ "model.language_model.layers.52.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
648
+ "model.language_model.layers.52.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
649
+ "model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
650
+ "model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
651
+ "model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
652
+ "model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
653
+ "model.language_model.layers.52.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
654
+ "model.language_model.layers.52.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
655
+ "model.language_model.layers.52.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
656
+ "model.language_model.layers.52.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
657
+ "model.language_model.layers.52.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
658
+ "model.language_model.layers.52.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
659
+ "model.language_model.layers.53.input_layernorm.weight": "model-00002-of-00003.safetensors",
660
+ "model.language_model.layers.53.linear_attn.A_log": "model-00002-of-00003.safetensors",
661
+ "model.language_model.layers.53.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
662
+ "model.language_model.layers.53.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
663
+ "model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
664
+ "model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
665
+ "model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
666
+ "model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
667
+ "model.language_model.layers.53.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
668
+ "model.language_model.layers.53.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
669
+ "model.language_model.layers.53.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
670
+ "model.language_model.layers.53.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
671
+ "model.language_model.layers.53.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
672
+ "model.language_model.layers.53.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
673
+ "model.language_model.layers.54.input_layernorm.weight": "model-00002-of-00003.safetensors",
674
+ "model.language_model.layers.54.linear_attn.A_log": "model-00002-of-00003.safetensors",
675
+ "model.language_model.layers.54.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
676
+ "model.language_model.layers.54.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
677
+ "model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
678
+ "model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
679
+ "model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
680
+ "model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
681
+ "model.language_model.layers.54.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
682
+ "model.language_model.layers.54.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
683
+ "model.language_model.layers.54.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
684
+ "model.language_model.layers.54.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
685
+ "model.language_model.layers.54.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
686
+ "model.language_model.layers.54.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
687
+ "model.language_model.layers.55.input_layernorm.weight": "model-00002-of-00003.safetensors",
688
+ "model.language_model.layers.55.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
689
+ "model.language_model.layers.55.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
690
+ "model.language_model.layers.55.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
691
+ "model.language_model.layers.55.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
692
+ "model.language_model.layers.55.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
693
+ "model.language_model.layers.55.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
694
+ "model.language_model.layers.55.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
695
+ "model.language_model.layers.55.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
696
+ "model.language_model.layers.55.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
697
+ "model.language_model.layers.55.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
698
+ "model.language_model.layers.56.input_layernorm.weight": "model-00002-of-00003.safetensors",
699
+ "model.language_model.layers.56.linear_attn.A_log": "model-00002-of-00003.safetensors",
700
+ "model.language_model.layers.56.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
701
+ "model.language_model.layers.56.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
702
+ "model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
703
+ "model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
704
+ "model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
705
+ "model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
706
+ "model.language_model.layers.56.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
707
+ "model.language_model.layers.56.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
708
+ "model.language_model.layers.56.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
709
+ "model.language_model.layers.56.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
710
+ "model.language_model.layers.56.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
711
+ "model.language_model.layers.56.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
712
+ "model.language_model.layers.57.input_layernorm.weight": "model-00002-of-00003.safetensors",
713
+ "model.language_model.layers.57.linear_attn.A_log": "model-00002-of-00003.safetensors",
714
+ "model.language_model.layers.57.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
715
+ "model.language_model.layers.57.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
716
+ "model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
717
+ "model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
718
+ "model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
719
+ "model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
720
+ "model.language_model.layers.57.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
721
+ "model.language_model.layers.57.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
722
+ "model.language_model.layers.57.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
723
+ "model.language_model.layers.57.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
724
+ "model.language_model.layers.57.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
725
+ "model.language_model.layers.57.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
726
+ "model.language_model.layers.58.input_layernorm.weight": "model-00002-of-00003.safetensors",
727
+ "model.language_model.layers.58.linear_attn.A_log": "model-00002-of-00003.safetensors",
728
+ "model.language_model.layers.58.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
729
+ "model.language_model.layers.58.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
730
+ "model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
731
+ "model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
732
+ "model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
733
+ "model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
734
+ "model.language_model.layers.58.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
735
+ "model.language_model.layers.58.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
736
+ "model.language_model.layers.58.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
737
+ "model.language_model.layers.58.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
738
+ "model.language_model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
739
+ "model.language_model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
740
+ "model.language_model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
741
+ "model.language_model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
742
+ "model.language_model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
743
+ "model.language_model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
744
+ "model.language_model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
745
+ "model.language_model.layers.59.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
746
+ "model.language_model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
747
+ "model.language_model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
748
+ "model.language_model.layers.59.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
749
+ "model.language_model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
750
+ "model.language_model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
751
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
752
+ "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00003.safetensors",
753
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
754
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
755
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
756
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
757
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
758
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
759
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
760
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
761
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
762
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
763
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
764
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
765
+ "model.language_model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
766
+ "model.language_model.layers.60.linear_attn.A_log": "model-00003-of-00003.safetensors",
767
+ "model.language_model.layers.60.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
768
+ "model.language_model.layers.60.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
769
+ "model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
770
+ "model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
771
+ "model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
772
+ "model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
773
+ "model.language_model.layers.60.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
774
+ "model.language_model.layers.60.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
775
+ "model.language_model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
776
+ "model.language_model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
777
+ "model.language_model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
778
+ "model.language_model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
779
+ "model.language_model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
780
+ "model.language_model.layers.61.linear_attn.A_log": "model-00003-of-00003.safetensors",
781
+ "model.language_model.layers.61.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
782
+ "model.language_model.layers.61.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
783
+ "model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
784
+ "model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
785
+ "model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
786
+ "model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
787
+ "model.language_model.layers.61.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
788
+ "model.language_model.layers.61.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
789
+ "model.language_model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
790
+ "model.language_model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
791
+ "model.language_model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
792
+ "model.language_model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
793
+ "model.language_model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
794
+ "model.language_model.layers.62.linear_attn.A_log": "model-00003-of-00003.safetensors",
795
+ "model.language_model.layers.62.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
796
+ "model.language_model.layers.62.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
797
+ "model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
798
+ "model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
799
+ "model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
800
+ "model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
801
+ "model.language_model.layers.62.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
802
+ "model.language_model.layers.62.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
803
+ "model.language_model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
804
+ "model.language_model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
805
+ "model.language_model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
806
+ "model.language_model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
807
+ "model.language_model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
808
+ "model.language_model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
809
+ "model.language_model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
810
+ "model.language_model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
811
+ "model.language_model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
812
+ "model.language_model.layers.63.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
813
+ "model.language_model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
814
+ "model.language_model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
815
+ "model.language_model.layers.63.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
816
+ "model.language_model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
817
+ "model.language_model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
818
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
819
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
820
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
821
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
822
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
823
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
824
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
825
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
826
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
827
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
828
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
829
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
830
+ "model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00003.safetensors",
831
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
832
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
833
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
834
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
835
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
836
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
837
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
838
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
839
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
840
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
841
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
842
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
843
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
844
+ "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00003.safetensors",
845
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
846
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
847
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
848
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
849
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
850
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
851
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
852
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
853
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
854
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
855
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
856
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
857
+ "model.language_model.norm.weight": "model-00003-of-00003.safetensors"
858
+ }
859
+ }
checkpoint-698/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713048b88b3f826a1ee139665c96b8e6911450a312bc956e02b49d8ab27afb6f
3
+ size 215168550582
checkpoint-698/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fac64c124267eed682a37de708b264f27b8c65ac214abb1acc6ab636c3e778a
3
+ size 107584408648
checkpoint-698/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e5f48b40f283c2be57ffeca20c84e74d5bad51d76da17d127991b78da5289d
3
+ size 16389
checkpoint-698/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3696205cbf4679a7f2faf48351e924c79ada4cfd81a956e03e4319cf3d05b5
3
+ size 16389
checkpoint-698/rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e959ec0a3177f86cb76d0a9baecc2d6a28341309c4dba0a9e4c278b7c433be
3
+ size 16404
checkpoint-698/rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b590b91a591f4d07ae7135ca9bc378d1d9deec333422a9962a3306ffd6f4a2e6
3
+ size 16404
checkpoint-698/rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b629b9f615b6885bf51a6a684eed3edbc536f006e5eb0c2ecc091b1f08ef3463
3
+ size 16404
checkpoint-698/rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02659154a3f57bad7819341c0b66fe17f2389c4ba4e6bd8e8441e8715c662b51
3
+ size 16404
checkpoint-698/rng_state_14.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c9bf190d66ea3267b5e39eaa3b79a00b4f6f705c35149ffcd1ee979a441d57
3
+ size 16404
checkpoint-698/rng_state_15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ceb356592ffa9a48299d85910169bd0d603aeac5e8463e5fb102164f8bd41b1
3
+ size 16404
checkpoint-698/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403766b1961af9b11405f33af2b272a2d6287cefdee9eb7e26e1dc71e3ed3707
3
+ size 16389
checkpoint-698/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f6e3e08fea79c105dbd92657538a3cb15e89872360a3c3072b758835ca5ebc
3
+ size 16389
checkpoint-698/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0203808a2df05d235c57b83a0a087bae98ef6e47f06d685a0bddaa460a16c910
3
+ size 16389
checkpoint-698/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b492b10406611c53f05fd065d6968c7e5e3797fd0008fca46cad009936c67e
3
+ size 16389
checkpoint-698/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44646ad1e32ad260756d9c2e6927a7a101af3a5c9265d8db8a1d4def7d446cb
3
+ size 16389
checkpoint-698/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b83b78288d5cea0b10985a2d48c3c0b12d2ff3f99104720c1b3281409b3b752
3
+ size 16389
checkpoint-698/rng_state_8.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8cfe684f17455a3db72e9149b077f09138790a2ba8e34fab532395fda759f4
3
+ size 16389
checkpoint-698/rng_state_9.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d705a0963d8ac37075f7414863e2653f7d90affad0ff04203c4d715a1b7e22a
3
+ size 16389
checkpoint-698/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b05347e71e179172f6e609fcceeca27510e8802e8e589c1ee4d5e8d292bb18
3
+ size 1465
checkpoint-698/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
checkpoint-698/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "split_special_tokens": false,
26
+ "tokenizer_class": "TokenizersBackend",
27
+ "unk_token": null,
28
+ "video_token": "<|video_pad|>",
29
+ "vision_bos_token": "<|vision_start|>",
30
+ "vision_eos_token": "<|vision_end|>"
31
+ }
checkpoint-698/trainer_state.json ADDED
@@ -0,0 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 200,
7
+ "global_step": 698,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0014336917562724014,
14
+ "grad_norm": 5.102053642272949,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.1358120441436768,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.014336917562724014,
21
+ "grad_norm": 0.22924242913722992,
22
+ "learning_rate": 5.142857142857142e-06,
23
+ "loss": 0.5612610710991753,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.02867383512544803,
28
+ "grad_norm": 0.12333694845438004,
29
+ "learning_rate": 1.0857142857142858e-05,
30
+ "loss": 0.18545818328857422,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 0.043010752688172046,
35
+ "grad_norm": 0.14276181161403656,
36
+ "learning_rate": 1.6571428571428574e-05,
37
+ "loss": 0.16717807054519654,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.05734767025089606,
42
+ "grad_norm": 0.10264057666063309,
43
+ "learning_rate": 1.9998203820754213e-05,
44
+ "loss": 0.17055926322937012,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.07168458781362007,
49
+ "grad_norm": 0.104465052485466,
50
+ "learning_rate": 1.9978004213822736e-05,
51
+ "loss": 0.1625239610671997,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.08602150537634409,
56
+ "grad_norm": 0.10240382701158524,
57
+ "learning_rate": 1.993540527265239e-05,
58
+ "loss": 0.1715969681739807,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.1003584229390681,
63
+ "grad_norm": 0.08893006294965744,
64
+ "learning_rate": 1.9870502626379127e-05,
65
+ "loss": 0.16313509941101073,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.11469534050179211,
70
+ "grad_norm": 0.12808184325695038,
71
+ "learning_rate": 1.9783441973084023e-05,
72
+ "loss": 0.16091221570968628,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.12903225806451613,
77
+ "grad_norm": 0.08048602193593979,
78
+ "learning_rate": 1.9674418752719835e-05,
79
+ "loss": 0.15647590160369873,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.14336917562724014,
84
+ "grad_norm": 0.08210249245166779,
85
+ "learning_rate": 1.9543677708373496e-05,
86
+ "loss": 0.16005860567092894,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.15770609318996415,
91
+ "grad_norm": 0.0777139738202095,
92
+ "learning_rate": 1.9391512336849406e-05,
93
+ "loss": 0.15733616352081298,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.17204301075268819,
98
+ "grad_norm": 0.07640817761421204,
99
+ "learning_rate": 1.9218264229806917e-05,
100
+ "loss": 0.15088759660720824,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.1863799283154122,
105
+ "grad_norm": 0.08728871494531631,
106
+ "learning_rate": 1.9024322306931035e-05,
107
+ "loss": 0.1508031129837036,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 0.2007168458781362,
112
+ "grad_norm": 0.0811760425567627,
113
+ "learning_rate": 1.8810121942857848e-05,
114
+ "loss": 0.15035929679870605,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 0.21505376344086022,
119
+ "grad_norm": 0.08090047538280487,
120
+ "learning_rate": 1.8576143989814524e-05,
121
+ "loss": 0.15261363983154297,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 0.22939068100358423,
126
+ "grad_norm": 0.09918594360351562,
127
+ "learning_rate": 1.8322913698168014e-05,
128
+ "loss": 0.15076379776000975,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 0.24372759856630824,
133
+ "grad_norm": 0.08928713947534561,
134
+ "learning_rate": 1.8050999537305634e-05,
135
+ "loss": 0.15194735527038575,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 0.25806451612903225,
140
+ "grad_norm": 0.07266855984926224,
141
+ "learning_rate": 1.776101191949449e-05,
142
+ "loss": 0.15317165851593018,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 0.2724014336917563,
147
+ "grad_norm": 0.07347071915864944,
148
+ "learning_rate": 1.745360182958459e-05,
149
+ "loss": 0.15253105163574218,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 0.2867383512544803,
154
+ "grad_norm": 0.0758705884218216,
155
+ "learning_rate": 1.7129459363631692e-05,
156
+ "loss": 0.14779815673828126,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 0.2867383512544803,
161
+ "eval_loss": 0.2187168002128601,
162
+ "eval_runtime": 47.0917,
163
+ "eval_samples_per_second": 124.247,
164
+ "eval_steps_per_second": 0.255,
165
+ "step": 200
166
+ },
167
+ {
168
+ "epoch": 0.3010752688172043,
169
+ "grad_norm": 0.07489030808210373,
170
+ "learning_rate": 1.678931217972055e-05,
171
+ "loss": 0.14687340259552,
172
+ "step": 210
173
+ },
174
+ {
175
+ "epoch": 0.3154121863799283,
176
+ "grad_norm": 0.0788242295384407,
177
+ "learning_rate": 1.6433923864466235e-05,
178
+ "loss": 0.14286456108093262,
179
+ "step": 220
180
+ },
181
+ {
182
+ "epoch": 0.32974910394265233,
183
+ "grad_norm": 0.8215664029121399,
184
+ "learning_rate": 1.6064092218860553e-05,
185
+ "loss": 0.15229986906051635,
186
+ "step": 230
187
+ },
188
+ {
189
+ "epoch": 0.34408602150537637,
190
+ "grad_norm": 0.06975199282169342,
191
+ "learning_rate": 1.568064746731156e-05,
192
+ "loss": 0.14773318767547608,
193
+ "step": 240
194
+ },
195
+ {
196
+ "epoch": 0.35842293906810035,
197
+ "grad_norm": 0.07249259203672409,
198
+ "learning_rate": 1.5284450393896713e-05,
199
+ "loss": 0.15218548774719237,
200
+ "step": 250
201
+ },
202
+ {
203
+ "epoch": 0.3727598566308244,
204
+ "grad_norm": 0.07201112061738968,
205
+ "learning_rate": 1.4876390410013498e-05,
206
+ "loss": 0.14689412117004394,
207
+ "step": 260
208
+ },
209
+ {
210
+ "epoch": 0.3870967741935484,
211
+ "grad_norm": 0.06810774654150009,
212
+ "learning_rate": 1.4457383557765385e-05,
213
+ "loss": 0.14651920795440673,
214
+ "step": 270
215
+ },
216
+ {
217
+ "epoch": 0.4014336917562724,
218
+ "grad_norm": 0.06508651375770569,
219
+ "learning_rate": 1.402837045356531e-05,
220
+ "loss": 0.1467513084411621,
221
+ "step": 280
222
+ },
223
+ {
224
+ "epoch": 0.4157706093189964,
225
+ "grad_norm": 0.06673789769411087,
226
+ "learning_rate": 1.3590314176572989e-05,
227
+ "loss": 0.13457820415496827,
228
+ "step": 290
229
+ },
230
+ {
231
+ "epoch": 0.43010752688172044,
232
+ "grad_norm": 0.07056573778390884,
233
+ "learning_rate": 1.314419810670624e-05,
234
+ "loss": 0.14077857732772828,
235
+ "step": 300
236
+ },
237
+ {
238
+ "epoch": 0.4444444444444444,
239
+ "grad_norm": 0.06851952522993088,
240
+ "learning_rate": 1.2691023717079735e-05,
241
+ "loss": 0.138556170463562,
242
+ "step": 310
243
+ },
244
+ {
245
+ "epoch": 0.45878136200716846,
246
+ "grad_norm": 0.06733077019453049,
247
+ "learning_rate": 1.2231808325826862e-05,
248
+ "loss": 0.13921281099319457,
249
+ "step": 320
250
+ },
251
+ {
252
+ "epoch": 0.4731182795698925,
253
+ "grad_norm": 0.07425093650817871,
254
+ "learning_rate": 1.176758281235155e-05,
255
+ "loss": 0.13010122776031494,
256
+ "step": 330
257
+ },
258
+ {
259
+ "epoch": 0.4874551971326165,
260
+ "grad_norm": 0.06684776395559311,
261
+ "learning_rate": 1.129938930313678e-05,
262
+ "loss": 0.1314706802368164,
263
+ "step": 340
264
+ },
265
+ {
266
+ "epoch": 0.5017921146953405,
267
+ "grad_norm": 0.06619785726070404,
268
+ "learning_rate": 1.082827883230487e-05,
269
+ "loss": 0.13385097980499266,
270
+ "step": 350
271
+ },
272
+ {
273
+ "epoch": 0.5161290322580645,
274
+ "grad_norm": 0.07259789854288101,
275
+ "learning_rate": 1.0355308982181254e-05,
276
+ "loss": 0.13582653999328614,
277
+ "step": 360
278
+ },
279
+ {
280
+ "epoch": 0.5304659498207885,
281
+ "grad_norm": 0.06673564016819,
282
+ "learning_rate": 9.881541509158366e-06,
283
+ "loss": 0.1326061010360718,
284
+ "step": 370
285
+ },
286
+ {
287
+ "epoch": 0.5448028673835126,
288
+ "grad_norm": 0.0609956830739975,
289
+ "learning_rate": 9.408039960189317e-06,
290
+ "loss": 0.12904767990112304,
291
+ "step": 380
292
+ },
293
+ {
294
+ "epoch": 0.5591397849462365,
295
+ "grad_norm": 0.07004307955503464,
296
+ "learning_rate": 8.935867285261977e-06,
297
+ "loss": 0.14127167463302612,
298
+ "step": 390
299
+ },
300
+ {
301
+ "epoch": 0.5734767025089605,
302
+ "grad_norm": 0.06114516407251358,
303
+ "learning_rate": 8.466083451213145e-06,
304
+ "loss": 0.13098690509796143,
305
+ "step": 400
306
+ },
307
+ {
308
+ "epoch": 0.5734767025089605,
309
+ "eval_loss": 0.1937306523323059,
310
+ "eval_runtime": 47.434,
311
+ "eval_samples_per_second": 123.35,
312
+ "eval_steps_per_second": 0.253,
313
+ "step": 400
314
+ },
315
+ {
316
+ "epoch": 0.5878136200716846,
317
+ "grad_norm": 0.07561196386814117,
318
+ "learning_rate": 7.999743062239557e-06,
319
+ "loss": 0.13492929935455322,
320
+ "step": 410
321
+ },
322
+ {
323
+ "epoch": 0.6021505376344086,
324
+ "grad_norm": 0.06452950835227966,
325
+ "learning_rate": 7.5378929924472735e-06,
326
+ "loss": 0.13134829998016356,
327
+ "step": 420
328
+ },
329
+ {
330
+ "epoch": 0.6164874551971327,
331
+ "grad_norm": 0.05738452449440956,
332
+ "learning_rate": 7.081570035754189e-06,
333
+ "loss": 0.1305772066116333,
334
+ "step": 430
335
+ },
336
+ {
337
+ "epoch": 0.6308243727598566,
338
+ "grad_norm": 0.06140970438718796,
339
+ "learning_rate": 6.631798578421195e-06,
340
+ "loss": 0.12945042848587035,
341
+ "step": 440
342
+ },
343
+ {
344
+ "epoch": 0.6451612903225806,
345
+ "grad_norm": 0.0673835426568985,
346
+ "learning_rate": 6.189588299436997e-06,
347
+ "loss": 0.133364737033844,
348
+ "step": 450
349
+ },
350
+ {
351
+ "epoch": 0.6594982078853047,
352
+ "grad_norm": 0.06186283379793167,
353
+ "learning_rate": 5.755931903918835e-06,
354
+ "loss": 0.12029262781143188,
355
+ "step": 460
356
+ },
357
+ {
358
+ "epoch": 0.6738351254480287,
359
+ "grad_norm": 0.061157312244176865,
360
+ "learning_rate": 5.331802894617333e-06,
361
+ "loss": 0.12551844120025635,
362
+ "step": 470
363
+ },
364
+ {
365
+ "epoch": 0.6881720430107527,
366
+ "grad_norm": 0.06083202734589577,
367
+ "learning_rate": 4.918153386528271e-06,
368
+ "loss": 0.12006042003631592,
369
+ "step": 480
370
+ },
371
+ {
372
+ "epoch": 0.7025089605734767,
373
+ "grad_norm": 0.05786828324198723,
374
+ "learning_rate": 4.515911969516985e-06,
375
+ "loss": 0.12329277992248536,
376
+ "step": 490
377
+ },
378
+ {
379
+ "epoch": 0.7168458781362007,
380
+ "grad_norm": 0.07877270132303238,
381
+ "learning_rate": 4.125981623753801e-06,
382
+ "loss": 0.1233370542526245,
383
+ "step": 500
384
+ },
385
+ {
386
+ "epoch": 0.7311827956989247,
387
+ "grad_norm": 0.06246776878833771,
388
+ "learning_rate": 3.7492376926397966e-06,
389
+ "loss": 0.12439545392990112,
390
+ "step": 510
391
+ },
392
+ {
393
+ "epoch": 0.7455197132616488,
394
+ "grad_norm": 0.06481961905956268,
395
+ "learning_rate": 3.3865259177736663e-06,
396
+ "loss": 0.12364455461502075,
397
+ "step": 520
398
+ },
399
+ {
400
+ "epoch": 0.7598566308243727,
401
+ "grad_norm": 0.0777650848031044,
402
+ "learning_rate": 3.0386605403707347e-06,
403
+ "loss": 0.1195528745651245,
404
+ "step": 530
405
+ },
406
+ {
407
+ "epoch": 0.7741935483870968,
408
+ "grad_norm": 0.05968371778726578,
409
+ "learning_rate": 2.7064224733963197e-06,
410
+ "loss": 0.1176903247833252,
411
+ "step": 540
412
+ },
413
+ {
414
+ "epoch": 0.7885304659498208,
415
+ "grad_norm": 0.059006717056035995,
416
+ "learning_rate": 2.3905575485167098e-06,
417
+ "loss": 0.12136919498443603,
418
+ "step": 550
419
+ },
420
+ {
421
+ "epoch": 0.8028673835125448,
422
+ "grad_norm": 0.062085703015327454,
423
+ "learning_rate": 2.0917748418031415e-06,
424
+ "loss": 0.1185749888420105,
425
+ "step": 560
426
+ },
427
+ {
428
+ "epoch": 0.8172043010752689,
429
+ "grad_norm": 0.05684107542037964,
430
+ "learning_rate": 1.8107450819473505e-06,
431
+ "loss": 0.12052475214004517,
432
+ "step": 570
433
+ },
434
+ {
435
+ "epoch": 0.8315412186379928,
436
+ "grad_norm": 0.056005772203207016,
437
+ "learning_rate": 1.5480991445620541e-06,
438
+ "loss": 0.11635445356369019,
439
+ "step": 580
440
+ },
441
+ {
442
+ "epoch": 0.8458781362007168,
443
+ "grad_norm": 0.08036984503269196,
444
+ "learning_rate": 1.3044266359464542e-06,
445
+ "loss": 0.12693744897842407,
446
+ "step": 590
447
+ },
448
+ {
449
+ "epoch": 0.8602150537634409,
450
+ "grad_norm": 0.05893237143754959,
451
+ "learning_rate": 1.080274569496057e-06,
452
+ "loss": 0.11600825786590577,
453
+ "step": 600
454
+ },
455
+ {
456
+ "epoch": 0.8602150537634409,
457
+ "eval_loss": 0.17753292620182037,
458
+ "eval_runtime": 48.0542,
459
+ "eval_samples_per_second": 121.758,
460
+ "eval_steps_per_second": 0.25,
461
+ "step": 600
462
+ },
463
+ {
464
+ "epoch": 0.8745519713261649,
465
+ "grad_norm": 0.06269249320030212,
466
+ "learning_rate": 8.761461377280311e-07,
467
+ "loss": 0.11844503879547119,
468
+ "step": 610
469
+ },
470
+ {
471
+ "epoch": 0.8888888888888888,
472
+ "grad_norm": 0.06056367605924606,
473
+ "learning_rate": 6.924995826788516e-07,
474
+ "loss": 0.1225665807723999,
475
+ "step": 620
476
+ },
477
+ {
478
+ "epoch": 0.9032258064516129,
479
+ "grad_norm": 0.05936103314161301,
480
+ "learning_rate": 5.29747167209923e-07,
481
+ "loss": 0.11874287128448487,
482
+ "step": 630
483
+ },
484
+ {
485
+ "epoch": 0.9175627240143369,
486
+ "grad_norm": 0.06041805073618889,
487
+ "learning_rate": 3.88254249530583e-07,
488
+ "loss": 0.11610586643218994,
489
+ "step": 640
490
+ },
491
+ {
492
+ "epoch": 0.931899641577061,
493
+ "grad_norm": 0.0608358308672905,
494
+ "learning_rate": 2.6833846301596246e-07,
495
+ "loss": 0.11917197704315186,
496
+ "step": 650
497
+ },
498
+ {
499
+ "epoch": 0.946236559139785,
500
+ "grad_norm": 0.0607263408601284,
501
+ "learning_rate": 1.7026900316098217e-07,
502
+ "loss": 0.11865537166595459,
503
+ "step": 660
504
+ },
505
+ {
506
+ "epoch": 0.9605734767025089,
507
+ "grad_norm": 0.05322834476828575,
508
+ "learning_rate": 9.426602327113788e-08,
509
+ "loss": 0.11138832569122314,
510
+ "step": 670
511
+ },
512
+ {
513
+ "epoch": 0.974910394265233,
514
+ "grad_norm": 0.06341966986656189,
515
+ "learning_rate": 4.050014024668425e-08,
516
+ "loss": 0.11363672018051148,
517
+ "step": 680
518
+ },
519
+ {
520
+ "epoch": 0.989247311827957,
521
+ "grad_norm": 0.06364062428474426,
522
+ "learning_rate": 9.092051569674632e-09,
523
+ "loss": 0.12197227478027343,
524
+ "step": 690
525
+ },
526
+ {
527
+ "epoch": 1.0,
528
+ "eval_loss": 0.17584605515003204,
529
+ "eval_runtime": 49.4161,
530
+ "eval_samples_per_second": 118.403,
531
+ "eval_steps_per_second": 0.243,
532
+ "step": 698
533
+ }
534
+ ],
535
+ "logging_steps": 10,
536
+ "max_steps": 698,
537
+ "num_input_tokens_seen": 0,
538
+ "num_train_epochs": 1,
539
+ "save_steps": 500,
540
+ "stateful_callbacks": {
541
+ "TrainerControl": {
542
+ "args": {
543
+ "should_epoch_stop": false,
544
+ "should_evaluate": false,
545
+ "should_log": false,
546
+ "should_save": true,
547
+ "should_training_stop": true
548
+ },
549
+ "attributes": {}
550
+ }
551
+ },
552
+ "total_flos": 2.2148830443916493e+17,
553
+ "train_batch_size": 2,
554
+ "trial_name": null,
555
+ "trial_params": null
556
+ }
checkpoint-698/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac996115f252ffd276ca5d0ff9fadf215f59ab46f9e6fcf21c28f054aecca9b
3
+ size 5201
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 17408,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention"
84
+ ],
85
+ "linear_conv_kernel_dim": 4,
86
+ "linear_key_head_dim": 128,
87
+ "linear_num_key_heads": 16,
88
+ "linear_num_value_heads": 48,
89
+ "linear_value_head_dim": 128,
90
+ "max_position_embeddings": 262144,
91
+ "mlp_only_layers": [],
92
+ "model_type": "qwen3_5_text",
93
+ "mtp_num_hidden_layers": 1,
94
+ "mtp_use_dedicated_embeddings": false,
95
+ "num_attention_heads": 24,
96
+ "num_hidden_layers": 64,
97
+ "num_key_value_heads": 4,
98
+ "rms_norm_eps": 1e-06,
99
+ "use_cache": true,
100
+ "vocab_size": 248320,
101
+ "mamba_ssm_dtype": "float32",
102
+ "rope_parameters": {
103
+ "mrope_interleaved": true,
104
+ "mrope_section": [
105
+ 11,
106
+ 11,
107
+ 10
108
+ ],
109
+ "rope_type": "default",
110
+ "rope_theta": 10000000,
111
+ "partial_rotary_factor": 0.25
112
+ }
113
+ },
114
+ "tie_word_embeddings": false,
115
+ "transformers_version": "4.57.0.dev0",
116
+ "video_token_id": 248057,
117
+ "vision_config": {
118
+ "deepstack_visual_indexes": [],
119
+ "depth": 27,
120
+ "hidden_act": "gelu_pytorch_tanh",
121
+ "hidden_size": 1152,
122
+ "in_channels": 3,
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 4304,
125
+ "model_type": "qwen3_5",
126
+ "num_heads": 16,
127
+ "num_position_embeddings": 2304,
128
+ "out_hidden_size": 5120,
129
+ "patch_size": 16,
130
+ "spatial_merge_size": 2,
131
+ "temporal_patch_size": 2
132
+ },
133
+ "vision_end_token_id": 248054,
134
+ "vision_start_token_id": 248053
135
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.0.dev0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f64b9eb55249a390f634753d9fd3a1d4902214dfa384b3275278968a268865
3
+ size 49979080424
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840952a248fdcb13de4834428baf32b82e53d9572ffbfd26cc3b17d3ae906773
3
+ size 49671140304
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30e39f7a3d9dde91061a883c9d1c35045772937c3e17e1372b665c933940a77
3
+ size 7933885616
model-visual.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d947ce7483c4109b55039f1359f4494d22390cf123568100abd89816802f097d
3
+ size 2148512760
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + 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\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\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 {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\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 {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }