Hugging Face's logo

Hcompany
/
Holo-3.1-35B-A3B-GGUF

Image-Text-to-Text
Transformers
GGUF
PyTorch
English
multimodal
action
agent
computer use
gui agents
Mixture of Experts
conversational
Model card Files
xet
 Community
1
avshalom-h commited on
Commit
d6ec177
·
verified ·
1 Parent(s): 18b3244

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .gitattributes +4 -0
  2. chat_template.jinja +154 -0
  3. convert_main.log +945 -0
  4. convert_mmproj.log +372 -0
  5. imatrix.gguf +3 -0
  6. imatrix.log +0 -0
  7. main.bf16.gguf +3 -0
  8. mmproj.f16.gguf +3 -0
  9. q4_k_m.gguf +3 -0
  10. quantize_q4_k_m.log +0 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ imatrix.gguf filter=lfs diff=lfs merge=lfs -text
37
+ main.bf16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ mmproj.f16.gguf filter=lfs diff=lfs merge=lfs -text
39
+ q4_k_m.gguf 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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}
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 %}
convert_main.log ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ INFO:hf-to-gguf:Loading model: source_model
2
+ INFO:hf-to-gguf:Model architecture: Qwen3_5MoeForConditionalGeneration
3
+ INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
4
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00026.safetensors'
5
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00026.safetensors'
6
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00026.safetensors'
7
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00026.safetensors'
8
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00026.safetensors'
9
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00026.safetensors'
10
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00026.safetensors'
11
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00026.safetensors'
12
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00026.safetensors'
13
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00026.safetensors'
14
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00026.safetensors'
15
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00026.safetensors'
16
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00026.safetensors'
17
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00026.safetensors'
18
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00026.safetensors'
19
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00026.safetensors'
20
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00026.safetensors'
21
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00026.safetensors'
22
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00026.safetensors'
23
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00026.safetensors'
24
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00026.safetensors'
25
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00026.safetensors'
26
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00026.safetensors'
27
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00026.safetensors'
28
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00026.safetensors'
29
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00026.safetensors'
30
+ INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
31
+ INFO:hf-to-gguf:Exporting model...
32
+ INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
33
+ INFO:hf-to-gguf:blk.0.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
34
+ INFO:hf-to-gguf:blk.0.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
35
+ INFO:hf-to-gguf:blk.0.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
36
+ INFO:hf-to-gguf:blk.0.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
37
+ INFO:hf-to-gguf:blk.0.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
38
+ INFO:hf-to-gguf:blk.1.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
39
+ INFO:hf-to-gguf:blk.1.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
40
+ INFO:hf-to-gguf:blk.1.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
41
+ INFO:hf-to-gguf:blk.1.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
42
+ INFO:hf-to-gguf:blk.1.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
43
+ INFO:hf-to-gguf:blk.1.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
44
+ INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
45
+ INFO:hf-to-gguf:blk.0.ssm_a, torch.bfloat16 --> F32, shape = {32}
46
+ INFO:hf-to-gguf:blk.0.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
47
+ INFO:hf-to-gguf:blk.0.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
48
+ INFO:hf-to-gguf:blk.0.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
49
+ INFO:hf-to-gguf:blk.0.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
50
+ INFO:hf-to-gguf:blk.0.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
51
+ INFO:hf-to-gguf:blk.0.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
52
+ INFO:hf-to-gguf:blk.0.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
53
+ INFO:hf-to-gguf:blk.0.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
54
+ INFO:hf-to-gguf:blk.0.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
55
+ INFO:hf-to-gguf:blk.0.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
56
+ INFO:hf-to-gguf:blk.0.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
57
+ INFO:hf-to-gguf:blk.0.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
58
+ INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
59
+ INFO:hf-to-gguf:blk.1.ssm_a, torch.bfloat16 --> F32, shape = {32}
60
+ INFO:hf-to-gguf:blk.1.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
61
+ INFO:hf-to-gguf:blk.1.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
62
+ INFO:hf-to-gguf:blk.1.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
63
+ INFO:hf-to-gguf:blk.1.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
64
+ INFO:hf-to-gguf:blk.1.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
65
+ INFO:hf-to-gguf:blk.1.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
66
+ INFO:hf-to-gguf:blk.1.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
67
+ INFO:hf-to-gguf:blk.1.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
68
+ INFO:hf-to-gguf:blk.1.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
69
+ INFO:hf-to-gguf:blk.1.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
70
+ INFO:hf-to-gguf:blk.1.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
71
+ INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
72
+ INFO:hf-to-gguf:blk.2.ssm_a, torch.bfloat16 --> F32, shape = {32}
73
+ INFO:hf-to-gguf:blk.2.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
74
+ INFO:hf-to-gguf:blk.2.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
75
+ INFO:hf-to-gguf:blk.2.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
76
+ INFO:hf-to-gguf:blk.2.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
77
+ INFO:hf-to-gguf:blk.2.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
78
+ INFO:hf-to-gguf:blk.2.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
79
+ INFO:hf-to-gguf:blk.2.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
80
+ INFO:hf-to-gguf:blk.2.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
81
+ INFO:hf-to-gguf:blk.2.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
82
+ INFO:hf-to-gguf:blk.2.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
83
+ INFO:hf-to-gguf:blk.2.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
84
+ INFO:hf-to-gguf:blk.2.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
85
+ INFO:hf-to-gguf:blk.2.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
86
+ INFO:hf-to-gguf:blk.2.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
87
+ INFO:hf-to-gguf:blk.2.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
88
+ INFO:hf-to-gguf:blk.2.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
89
+ INFO:hf-to-gguf:blk.2.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
90
+ INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
91
+ INFO:hf-to-gguf:blk.3.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
92
+ INFO:hf-to-gguf:blk.3.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
93
+ INFO:hf-to-gguf:blk.3.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
94
+ INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
95
+ INFO:hf-to-gguf:blk.3.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
96
+ INFO:hf-to-gguf:blk.3.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
97
+ INFO:hf-to-gguf:blk.3.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
98
+ INFO:hf-to-gguf:blk.3.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
99
+ INFO:hf-to-gguf:blk.3.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
100
+ INFO:hf-to-gguf:blk.3.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
101
+ INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
102
+ INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
103
+ INFO:hf-to-gguf:blk.3.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
104
+ INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
105
+ INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
106
+ INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
107
+ INFO:hf-to-gguf:blk.4.ssm_a, torch.bfloat16 --> F32, shape = {32}
108
+ INFO:hf-to-gguf:blk.4.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
109
+ INFO:hf-to-gguf:blk.4.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
110
+ INFO:hf-to-gguf:blk.4.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
111
+ INFO:hf-to-gguf:blk.4.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
112
+ INFO:hf-to-gguf:blk.4.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
113
+ INFO:hf-to-gguf:blk.4.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
114
+ INFO:hf-to-gguf:blk.4.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
115
+ INFO:hf-to-gguf:blk.4.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
116
+ INFO:hf-to-gguf:blk.4.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
117
+ INFO:hf-to-gguf:blk.4.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
118
+ INFO:hf-to-gguf:blk.4.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
119
+ INFO:hf-to-gguf:blk.4.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
120
+ INFO:hf-to-gguf:blk.4.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
121
+ INFO:hf-to-gguf:blk.4.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
122
+ INFO:hf-to-gguf:blk.4.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
123
+ INFO:hf-to-gguf:blk.4.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
124
+ INFO:hf-to-gguf:blk.4.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
125
+ INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
126
+ INFO:hf-to-gguf:blk.5.ssm_a, torch.bfloat16 --> F32, shape = {32}
127
+ INFO:hf-to-gguf:blk.5.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
128
+ INFO:hf-to-gguf:blk.5.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
129
+ INFO:hf-to-gguf:blk.5.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
130
+ INFO:hf-to-gguf:blk.5.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
131
+ INFO:hf-to-gguf:blk.5.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
132
+ INFO:hf-to-gguf:blk.5.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
133
+ INFO:hf-to-gguf:blk.5.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
134
+ INFO:hf-to-gguf:blk.5.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
135
+ INFO:hf-to-gguf:blk.5.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
136
+ INFO:hf-to-gguf:blk.5.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
137
+ INFO:hf-to-gguf:blk.5.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
138
+ INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
139
+ INFO:hf-to-gguf:blk.5.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
140
+ INFO:hf-to-gguf:blk.5.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
141
+ INFO:hf-to-gguf:blk.5.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
142
+ INFO:hf-to-gguf:blk.5.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
143
+ INFO:hf-to-gguf:blk.5.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
144
+ INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
145
+ INFO:hf-to-gguf:blk.6.ssm_a, torch.bfloat16 --> F32, shape = {32}
146
+ INFO:hf-to-gguf:blk.6.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
147
+ INFO:hf-to-gguf:blk.6.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
148
+ INFO:hf-to-gguf:blk.6.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
149
+ INFO:hf-to-gguf:blk.6.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
150
+ INFO:hf-to-gguf:blk.6.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
151
+ INFO:hf-to-gguf:blk.6.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
152
+ INFO:hf-to-gguf:blk.6.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
153
+ INFO:hf-to-gguf:blk.6.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
154
+ INFO:hf-to-gguf:blk.6.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
155
+ INFO:hf-to-gguf:blk.6.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
156
+ INFO:hf-to-gguf:blk.6.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
157
+ INFO:hf-to-gguf:blk.6.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
158
+ INFO:hf-to-gguf:blk.6.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
159
+ INFO:hf-to-gguf:blk.6.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
160
+ INFO:hf-to-gguf:blk.6.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
161
+ INFO:hf-to-gguf:blk.6.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
162
+ INFO:hf-to-gguf:blk.6.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
163
+ INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
164
+ INFO:hf-to-gguf:blk.7.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
165
+ INFO:hf-to-gguf:blk.7.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
166
+ INFO:hf-to-gguf:blk.7.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
167
+ INFO:hf-to-gguf:blk.7.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
168
+ INFO:hf-to-gguf:blk.7.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
169
+ INFO:hf-to-gguf:blk.7.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
170
+ INFO:hf-to-gguf:blk.7.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
171
+ INFO:hf-to-gguf:blk.7.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
172
+ INFO:hf-to-gguf:blk.7.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
173
+ INFO:hf-to-gguf:blk.7.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
174
+ INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
175
+ INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
176
+ INFO:hf-to-gguf:blk.7.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
177
+ INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
178
+ INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
179
+ INFO:hf-to-gguf:blk.10.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
180
+ INFO:hf-to-gguf:blk.10.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
181
+ INFO:hf-to-gguf:blk.10.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
182
+ INFO:hf-to-gguf:blk.10.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
183
+ INFO:hf-to-gguf:blk.8.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
184
+ INFO:hf-to-gguf:blk.8.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
185
+ INFO:hf-to-gguf:blk.8.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
186
+ INFO:hf-to-gguf:blk.8.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
187
+ INFO:hf-to-gguf:blk.8.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
188
+ INFO:hf-to-gguf:blk.8.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
189
+ INFO:hf-to-gguf:blk.9.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
190
+ INFO:hf-to-gguf:blk.9.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
191
+ INFO:hf-to-gguf:blk.9.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
192
+ INFO:hf-to-gguf:blk.9.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
193
+ INFO:hf-to-gguf:blk.9.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
194
+ INFO:hf-to-gguf:blk.9.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
195
+ INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
196
+ INFO:hf-to-gguf:blk.10.ssm_a, torch.bfloat16 --> F32, shape = {32}
197
+ INFO:hf-to-gguf:blk.10.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
198
+ INFO:hf-to-gguf:blk.10.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
199
+ INFO:hf-to-gguf:blk.10.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
200
+ INFO:hf-to-gguf:blk.10.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
201
+ INFO:hf-to-gguf:blk.10.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
202
+ INFO:hf-to-gguf:blk.10.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
203
+ INFO:hf-to-gguf:blk.10.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
204
+ INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
205
+ INFO:hf-to-gguf:blk.10.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
206
+ INFO:hf-to-gguf:blk.10.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
207
+ INFO:hf-to-gguf:blk.10.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
208
+ INFO:hf-to-gguf:blk.10.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
209
+ INFO:hf-to-gguf:blk.10.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
210
+ INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
211
+ INFO:hf-to-gguf:blk.8.ssm_a, torch.bfloat16 --> F32, shape = {32}
212
+ INFO:hf-to-gguf:blk.8.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
213
+ INFO:hf-to-gguf:blk.8.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
214
+ INFO:hf-to-gguf:blk.8.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
215
+ INFO:hf-to-gguf:blk.8.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
216
+ INFO:hf-to-gguf:blk.8.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
217
+ INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
218
+ INFO:hf-to-gguf:blk.8.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
219
+ INFO:hf-to-gguf:blk.8.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
220
+ INFO:hf-to-gguf:blk.8.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
221
+ INFO:hf-to-gguf:blk.8.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
222
+ INFO:hf-to-gguf:blk.8.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
223
+ INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
224
+ INFO:hf-to-gguf:blk.9.ssm_a, torch.bfloat16 --> F32, shape = {32}
225
+ INFO:hf-to-gguf:blk.9.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
226
+ INFO:hf-to-gguf:blk.9.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
227
+ INFO:hf-to-gguf:blk.9.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
228
+ INFO:hf-to-gguf:blk.9.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
229
+ INFO:hf-to-gguf:blk.9.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
230
+ INFO:hf-to-gguf:blk.9.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
231
+ INFO:hf-to-gguf:blk.9.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
232
+ INFO:hf-to-gguf:blk.9.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
233
+ INFO:hf-to-gguf:blk.9.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
234
+ INFO:hf-to-gguf:blk.9.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
235
+ INFO:hf-to-gguf:blk.9.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
236
+ INFO:hf-to-gguf:blk.11.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
237
+ INFO:hf-to-gguf:blk.11.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
238
+ INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
239
+ INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
240
+ INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
241
+ INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
242
+ INFO:hf-to-gguf:blk.12.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
243
+ INFO:hf-to-gguf:blk.12.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
244
+ INFO:hf-to-gguf:blk.12.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
245
+ INFO:hf-to-gguf:blk.12.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
246
+ INFO:hf-to-gguf:blk.12.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
247
+ INFO:hf-to-gguf:blk.13.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
248
+ INFO:hf-to-gguf:blk.13.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
249
+ INFO:hf-to-gguf:blk.13.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
250
+ INFO:hf-to-gguf:blk.13.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
251
+ INFO:hf-to-gguf:blk.13.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
252
+ INFO:hf-to-gguf:blk.13.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
253
+ INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
254
+ INFO:hf-to-gguf:blk.11.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
255
+ INFO:hf-to-gguf:blk.11.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
256
+ INFO:hf-to-gguf:blk.11.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
257
+ INFO:hf-to-gguf:blk.11.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
258
+ INFO:hf-to-gguf:blk.11.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
259
+ INFO:hf-to-gguf:blk.11.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
260
+ INFO:hf-to-gguf:blk.11.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
261
+ INFO:hf-to-gguf:blk.11.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
262
+ INFO:hf-to-gguf:blk.11.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
263
+ INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
264
+ INFO:hf-to-gguf:blk.12.ssm_a, torch.bfloat16 --> F32, shape = {32}
265
+ INFO:hf-to-gguf:blk.12.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
266
+ INFO:hf-to-gguf:blk.12.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
267
+ INFO:hf-to-gguf:blk.12.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
268
+ INFO:hf-to-gguf:blk.12.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
269
+ INFO:hf-to-gguf:blk.12.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
270
+ INFO:hf-to-gguf:blk.12.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
271
+ INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
272
+ INFO:hf-to-gguf:blk.12.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
273
+ INFO:hf-to-gguf:blk.12.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
274
+ INFO:hf-to-gguf:blk.12.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
275
+ INFO:hf-to-gguf:blk.12.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
276
+ INFO:hf-to-gguf:blk.12.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
277
+ INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
278
+ INFO:hf-to-gguf:blk.13.ssm_a, torch.bfloat16 --> F32, shape = {32}
279
+ INFO:hf-to-gguf:blk.13.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
280
+ INFO:hf-to-gguf:blk.13.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
281
+ INFO:hf-to-gguf:blk.13.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
282
+ INFO:hf-to-gguf:blk.13.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
283
+ INFO:hf-to-gguf:blk.13.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
284
+ INFO:hf-to-gguf:blk.13.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
285
+ INFO:hf-to-gguf:blk.13.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
286
+ INFO:hf-to-gguf:blk.13.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
287
+ INFO:hf-to-gguf:blk.13.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
288
+ INFO:hf-to-gguf:blk.13.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
289
+ INFO:hf-to-gguf:blk.13.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
290
+ INFO:hf-to-gguf:blk.14.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
291
+ INFO:hf-to-gguf:blk.14.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
292
+ INFO:hf-to-gguf:blk.14.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
293
+ INFO:hf-to-gguf:blk.14.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
294
+ INFO:hf-to-gguf:blk.14.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
295
+ INFO:hf-to-gguf:blk.14.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
296
+ INFO:hf-to-gguf:blk.15.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
297
+ INFO:hf-to-gguf:blk.15.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
298
+ INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
299
+ INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
300
+ INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
301
+ INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
302
+ INFO:hf-to-gguf:blk.16.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
303
+ INFO:hf-to-gguf:blk.16.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
304
+ INFO:hf-to-gguf:blk.16.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
305
+ INFO:hf-to-gguf:blk.16.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
306
+ INFO:hf-to-gguf:blk.16.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
307
+ INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
308
+ INFO:hf-to-gguf:blk.14.ssm_a, torch.bfloat16 --> F32, shape = {32}
309
+ INFO:hf-to-gguf:blk.14.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
310
+ INFO:hf-to-gguf:blk.14.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
311
+ INFO:hf-to-gguf:blk.14.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
312
+ INFO:hf-to-gguf:blk.14.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
313
+ INFO:hf-to-gguf:blk.14.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
314
+ INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
315
+ INFO:hf-to-gguf:blk.14.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
316
+ INFO:hf-to-gguf:blk.14.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
317
+ INFO:hf-to-gguf:blk.14.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
318
+ INFO:hf-to-gguf:blk.14.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
319
+ INFO:hf-to-gguf:blk.14.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
320
+ INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
321
+ INFO:hf-to-gguf:blk.15.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
322
+ INFO:hf-to-gguf:blk.15.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
323
+ INFO:hf-to-gguf:blk.15.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
324
+ INFO:hf-to-gguf:blk.15.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
325
+ INFO:hf-to-gguf:blk.15.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
326
+ INFO:hf-to-gguf:blk.15.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
327
+ INFO:hf-to-gguf:blk.15.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
328
+ INFO:hf-to-gguf:blk.15.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
329
+ INFO:hf-to-gguf:blk.15.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
330
+ INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
331
+ INFO:hf-to-gguf:blk.16.ssm_a, torch.bfloat16 --> F32, shape = {32}
332
+ INFO:hf-to-gguf:blk.16.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
333
+ INFO:hf-to-gguf:blk.16.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
334
+ INFO:hf-to-gguf:blk.16.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
335
+ INFO:hf-to-gguf:blk.16.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
336
+ INFO:hf-to-gguf:blk.16.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
337
+ INFO:hf-to-gguf:blk.16.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
338
+ INFO:hf-to-gguf:blk.16.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
339
+ INFO:hf-to-gguf:blk.16.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
340
+ INFO:hf-to-gguf:blk.16.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
341
+ INFO:hf-to-gguf:blk.16.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
342
+ INFO:hf-to-gguf:blk.16.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
343
+ INFO:hf-to-gguf:blk.16.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
344
+ INFO:hf-to-gguf:blk.17.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
345
+ INFO:hf-to-gguf:blk.17.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
346
+ INFO:hf-to-gguf:blk.17.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
347
+ INFO:hf-to-gguf:blk.17.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
348
+ INFO:hf-to-gguf:blk.17.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
349
+ INFO:hf-to-gguf:blk.17.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
350
+ INFO:hf-to-gguf:blk.18.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
351
+ INFO:hf-to-gguf:blk.18.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
352
+ INFO:hf-to-gguf:blk.18.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
353
+ INFO:hf-to-gguf:blk.18.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
354
+ INFO:hf-to-gguf:blk.19.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
355
+ INFO:hf-to-gguf:blk.19.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
356
+ INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
357
+ INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
358
+ INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
359
+ INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
360
+ INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
361
+ INFO:hf-to-gguf:blk.17.ssm_a, torch.bfloat16 --> F32, shape = {32}
362
+ INFO:hf-to-gguf:blk.17.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
363
+ INFO:hf-to-gguf:blk.17.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
364
+ INFO:hf-to-gguf:blk.17.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
365
+ INFO:hf-to-gguf:blk.17.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
366
+ INFO:hf-to-gguf:blk.17.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
367
+ INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
368
+ INFO:hf-to-gguf:blk.17.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
369
+ INFO:hf-to-gguf:blk.17.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
370
+ INFO:hf-to-gguf:blk.17.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
371
+ INFO:hf-to-gguf:blk.17.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
372
+ INFO:hf-to-gguf:blk.17.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
373
+ INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
374
+ INFO:hf-to-gguf:blk.18.ssm_a, torch.bfloat16 --> F32, shape = {32}
375
+ INFO:hf-to-gguf:blk.18.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
376
+ INFO:hf-to-gguf:blk.18.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
377
+ INFO:hf-to-gguf:blk.18.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
378
+ INFO:hf-to-gguf:blk.18.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
379
+ INFO:hf-to-gguf:blk.18.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
380
+ INFO:hf-to-gguf:blk.18.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
381
+ INFO:hf-to-gguf:blk.18.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
382
+ INFO:hf-to-gguf:blk.18.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
383
+ INFO:hf-to-gguf:blk.18.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
384
+ INFO:hf-to-gguf:blk.18.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
385
+ INFO:hf-to-gguf:blk.18.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
386
+ INFO:hf-to-gguf:blk.18.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
387
+ INFO:hf-to-gguf:blk.18.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
388
+ INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
389
+ INFO:hf-to-gguf:blk.19.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
390
+ INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
391
+ INFO:hf-to-gguf:blk.19.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
392
+ INFO:hf-to-gguf:blk.19.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
393
+ INFO:hf-to-gguf:blk.19.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
394
+ INFO:hf-to-gguf:blk.19.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
395
+ INFO:hf-to-gguf:blk.19.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
396
+ INFO:hf-to-gguf:blk.19.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
397
+ INFO:hf-to-gguf:blk.19.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
398
+ INFO:hf-to-gguf:blk.20.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
399
+ INFO:hf-to-gguf:blk.20.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
400
+ INFO:hf-to-gguf:blk.20.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
401
+ INFO:hf-to-gguf:blk.20.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
402
+ INFO:hf-to-gguf:blk.20.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
403
+ INFO:hf-to-gguf:blk.20.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
404
+ INFO:hf-to-gguf:blk.21.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
405
+ INFO:hf-to-gguf:blk.21.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
406
+ INFO:hf-to-gguf:blk.21.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
407
+ INFO:hf-to-gguf:blk.21.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
408
+ INFO:hf-to-gguf:blk.22.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
409
+ INFO:hf-to-gguf:blk.22.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
410
+ INFO:hf-to-gguf:blk.22.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
411
+ INFO:hf-to-gguf:blk.22.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
412
+ INFO:hf-to-gguf:blk.22.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
413
+ INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
414
+ INFO:hf-to-gguf:blk.20.ssm_a, torch.bfloat16 --> F32, shape = {32}
415
+ INFO:hf-to-gguf:blk.20.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
416
+ INFO:hf-to-gguf:blk.20.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
417
+ INFO:hf-to-gguf:blk.20.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
418
+ INFO:hf-to-gguf:blk.20.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
419
+ INFO:hf-to-gguf:blk.20.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
420
+ INFO:hf-to-gguf:blk.20.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
421
+ INFO:hf-to-gguf:blk.20.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
422
+ INFO:hf-to-gguf:blk.20.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
423
+ INFO:hf-to-gguf:blk.20.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
424
+ INFO:hf-to-gguf:blk.20.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
425
+ INFO:hf-to-gguf:blk.20.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
426
+ INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
427
+ INFO:hf-to-gguf:blk.21.ssm_a, torch.bfloat16 --> F32, shape = {32}
428
+ INFO:hf-to-gguf:blk.21.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
429
+ INFO:hf-to-gguf:blk.21.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
430
+ INFO:hf-to-gguf:blk.21.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
431
+ INFO:hf-to-gguf:blk.21.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
432
+ INFO:hf-to-gguf:blk.21.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
433
+ INFO:hf-to-gguf:blk.21.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
434
+ INFO:hf-to-gguf:blk.21.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
435
+ INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
436
+ INFO:hf-to-gguf:blk.21.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
437
+ INFO:hf-to-gguf:blk.21.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
438
+ INFO:hf-to-gguf:blk.21.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
439
+ INFO:hf-to-gguf:blk.21.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
440
+ INFO:hf-to-gguf:blk.21.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
441
+ INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
442
+ INFO:hf-to-gguf:blk.22.ssm_a, torch.bfloat16 --> F32, shape = {32}
443
+ INFO:hf-to-gguf:blk.22.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
444
+ INFO:hf-to-gguf:blk.22.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
445
+ INFO:hf-to-gguf:blk.22.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
446
+ INFO:hf-to-gguf:blk.22.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
447
+ INFO:hf-to-gguf:blk.22.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
448
+ INFO:hf-to-gguf:blk.22.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
449
+ INFO:hf-to-gguf:blk.22.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
450
+ INFO:hf-to-gguf:blk.22.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
451
+ INFO:hf-to-gguf:blk.22.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
452
+ INFO:hf-to-gguf:blk.22.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
453
+ INFO:hf-to-gguf:blk.22.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
454
+ INFO:hf-to-gguf:blk.22.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
455
+ INFO:hf-to-gguf:blk.23.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
456
+ INFO:hf-to-gguf:blk.23.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
457
+ INFO:hf-to-gguf:blk.23.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
458
+ INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
459
+ INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
460
+ INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
461
+ INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
462
+ INFO:hf-to-gguf:blk.24.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
463
+ INFO:hf-to-gguf:blk.24.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
464
+ INFO:hf-to-gguf:blk.24.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
465
+ INFO:hf-to-gguf:blk.24.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
466
+ INFO:hf-to-gguf:blk.24.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
467
+ INFO:hf-to-gguf:blk.24.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
468
+ INFO:hf-to-gguf:blk.25.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
469
+ INFO:hf-to-gguf:blk.25.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
470
+ INFO:hf-to-gguf:blk.25.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
471
+ INFO:hf-to-gguf:blk.25.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
472
+ INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
473
+ INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
474
+ INFO:hf-to-gguf:blk.23.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
475
+ INFO:hf-to-gguf:blk.23.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
476
+ INFO:hf-to-gguf:blk.23.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
477
+ INFO:hf-to-gguf:blk.23.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
478
+ INFO:hf-to-gguf:blk.23.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
479
+ INFO:hf-to-gguf:blk.23.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
480
+ INFO:hf-to-gguf:blk.23.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
481
+ INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
482
+ INFO:hf-to-gguf:blk.24.ssm_a, torch.bfloat16 --> F32, shape = {32}
483
+ INFO:hf-to-gguf:blk.24.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
484
+ INFO:hf-to-gguf:blk.24.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
485
+ INFO:hf-to-gguf:blk.24.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
486
+ INFO:hf-to-gguf:blk.24.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
487
+ INFO:hf-to-gguf:blk.24.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
488
+ INFO:hf-to-gguf:blk.24.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
489
+ INFO:hf-to-gguf:blk.24.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
490
+ INFO:hf-to-gguf:blk.24.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
491
+ INFO:hf-to-gguf:blk.24.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
492
+ INFO:hf-to-gguf:blk.24.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
493
+ INFO:hf-to-gguf:blk.24.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
494
+ INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
495
+ INFO:hf-to-gguf:blk.25.ssm_a, torch.bfloat16 --> F32, shape = {32}
496
+ INFO:hf-to-gguf:blk.25.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
497
+ INFO:hf-to-gguf:blk.25.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
498
+ INFO:hf-to-gguf:blk.25.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
499
+ INFO:hf-to-gguf:blk.25.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
500
+ INFO:hf-to-gguf:blk.25.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
501
+ INFO:hf-to-gguf:blk.25.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
502
+ INFO:hf-to-gguf:blk.25.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
503
+ INFO:hf-to-gguf:blk.25.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
504
+ INFO:hf-to-gguf:blk.25.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
505
+ INFO:hf-to-gguf:blk.25.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
506
+ INFO:hf-to-gguf:blk.25.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
507
+ INFO:hf-to-gguf:blk.25.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
508
+ INFO:hf-to-gguf:blk.25.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
509
+ INFO:hf-to-gguf:blk.26.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
510
+ INFO:hf-to-gguf:blk.26.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
511
+ INFO:hf-to-gguf:blk.26.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
512
+ INFO:hf-to-gguf:blk.26.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
513
+ INFO:hf-to-gguf:blk.26.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
514
+ INFO:hf-to-gguf:blk.27.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
515
+ INFO:hf-to-gguf:blk.27.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
516
+ INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
517
+ INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
518
+ INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
519
+ INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
520
+ INFO:hf-to-gguf:blk.28.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
521
+ INFO:hf-to-gguf:blk.28.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
522
+ INFO:hf-to-gguf:blk.28.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
523
+ INFO:hf-to-gguf:blk.28.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
524
+ INFO:hf-to-gguf:blk.28.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
525
+ INFO:hf-to-gguf:blk.28.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
526
+ INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
527
+ INFO:hf-to-gguf:blk.26.ssm_a, torch.bfloat16 --> F32, shape = {32}
528
+ INFO:hf-to-gguf:blk.26.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
529
+ INFO:hf-to-gguf:blk.26.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
530
+ INFO:hf-to-gguf:blk.26.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
531
+ INFO:hf-to-gguf:blk.26.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
532
+ INFO:hf-to-gguf:blk.26.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
533
+ INFO:hf-to-gguf:blk.26.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
534
+ INFO:hf-to-gguf:blk.26.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
535
+ INFO:hf-to-gguf:blk.26.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
536
+ INFO:hf-to-gguf:blk.26.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
537
+ INFO:hf-to-gguf:blk.26.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
538
+ INFO:hf-to-gguf:blk.26.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
539
+ INFO:hf-to-gguf:blk.26.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
540
+ INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
541
+ INFO:hf-to-gguf:blk.27.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
542
+ INFO:hf-to-gguf:blk.27.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
543
+ INFO:hf-to-gguf:blk.27.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
544
+ INFO:hf-to-gguf:blk.27.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
545
+ INFO:hf-to-gguf:blk.27.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
546
+ INFO:hf-to-gguf:blk.27.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
547
+ INFO:hf-to-gguf:blk.27.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
548
+ INFO:hf-to-gguf:blk.27.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
549
+ INFO:hf-to-gguf:blk.27.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
550
+ INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
551
+ INFO:hf-to-gguf:blk.28.ssm_a, torch.bfloat16 --> F32, shape = {32}
552
+ INFO:hf-to-gguf:blk.28.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
553
+ INFO:hf-to-gguf:blk.28.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
554
+ INFO:hf-to-gguf:blk.28.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
555
+ INFO:hf-to-gguf:blk.28.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
556
+ INFO:hf-to-gguf:blk.28.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
557
+ INFO:hf-to-gguf:blk.28.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
558
+ INFO:hf-to-gguf:blk.28.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
559
+ INFO:hf-to-gguf:blk.28.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
560
+ INFO:hf-to-gguf:blk.28.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
561
+ INFO:hf-to-gguf:blk.28.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
562
+ INFO:hf-to-gguf:blk.28.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
563
+ INFO:hf-to-gguf:blk.29.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
564
+ INFO:hf-to-gguf:blk.29.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
565
+ INFO:hf-to-gguf:blk.29.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
566
+ INFO:hf-to-gguf:blk.29.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
567
+ INFO:hf-to-gguf:blk.30.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
568
+ INFO:hf-to-gguf:blk.30.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
569
+ INFO:hf-to-gguf:blk.30.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
570
+ INFO:hf-to-gguf:blk.30.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
571
+ INFO:hf-to-gguf:blk.30.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
572
+ INFO:hf-to-gguf:blk.31.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
573
+ INFO:hf-to-gguf:blk.31.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
574
+ INFO:hf-to-gguf:blk.31.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
575
+ INFO:hf-to-gguf:blk.31.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
576
+ INFO:hf-to-gguf:blk.31.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
577
+ INFO:hf-to-gguf:blk.31.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
578
+ INFO:hf-to-gguf:blk.31.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
579
+ INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
580
+ INFO:hf-to-gguf:blk.29.ssm_a, torch.bfloat16 --> F32, shape = {32}
581
+ INFO:hf-to-gguf:blk.29.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
582
+ INFO:hf-to-gguf:blk.29.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
583
+ INFO:hf-to-gguf:blk.29.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
584
+ INFO:hf-to-gguf:blk.29.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
585
+ INFO:hf-to-gguf:blk.29.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
586
+ INFO:hf-to-gguf:blk.29.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
587
+ INFO:hf-to-gguf:blk.29.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
588
+ INFO:hf-to-gguf:blk.29.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
589
+ INFO:hf-to-gguf:blk.29.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
590
+ INFO:hf-to-gguf:blk.29.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
591
+ INFO:hf-to-gguf:blk.29.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
592
+ INFO:hf-to-gguf:blk.29.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
593
+ INFO:hf-to-gguf:blk.29.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
594
+ INFO:hf-to-gguf:blk.30.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
595
+ INFO:hf-to-gguf:blk.30.ssm_a, torch.bfloat16 --> F32, shape = {32}
596
+ INFO:hf-to-gguf:blk.30.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
597
+ INFO:hf-to-gguf:blk.30.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
598
+ INFO:hf-to-gguf:blk.30.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
599
+ INFO:hf-to-gguf:blk.30.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
600
+ INFO:hf-to-gguf:blk.30.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
601
+ INFO:hf-to-gguf:blk.30.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
602
+ INFO:hf-to-gguf:blk.30.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
603
+ INFO:hf-to-gguf:blk.30.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
604
+ INFO:hf-to-gguf:blk.30.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
605
+ INFO:hf-to-gguf:blk.30.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
606
+ INFO:hf-to-gguf:blk.30.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
607
+ INFO:hf-to-gguf:blk.30.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
608
+ INFO:hf-to-gguf:blk.31.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
609
+ INFO:hf-to-gguf:blk.31.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
610
+ INFO:hf-to-gguf:blk.31.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
611
+ INFO:hf-to-gguf:blk.31.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
612
+ INFO:hf-to-gguf:blk.31.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
613
+ INFO:hf-to-gguf:blk.31.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
614
+ INFO:hf-to-gguf:blk.31.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
615
+ INFO:hf-to-gguf:blk.31.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
616
+ INFO:hf-to-gguf:blk.31.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
617
+ INFO:hf-to-gguf:blk.32.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
618
+ INFO:hf-to-gguf:blk.32.ssm_a, torch.bfloat16 --> F32, shape = {32}
619
+ INFO:hf-to-gguf:blk.32.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
620
+ INFO:hf-to-gguf:blk.32.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
621
+ INFO:hf-to-gguf:blk.32.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
622
+ INFO:hf-to-gguf:blk.32.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
623
+ INFO:hf-to-gguf:blk.32.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
624
+ INFO:hf-to-gguf:blk.32.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
625
+ INFO:hf-to-gguf:blk.32.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
626
+ INFO:hf-to-gguf:blk.32.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
627
+ INFO:hf-to-gguf:blk.32.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
628
+ INFO:hf-to-gguf:blk.32.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
629
+ INFO:hf-to-gguf:blk.32.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
630
+ INFO:hf-to-gguf:blk.32.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
631
+ INFO:hf-to-gguf:blk.32.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
632
+ INFO:hf-to-gguf:blk.32.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
633
+ INFO:hf-to-gguf:blk.32.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
634
+ INFO:hf-to-gguf:blk.32.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
635
+ INFO:hf-to-gguf:blk.32.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
636
+ INFO:hf-to-gguf:blk.33.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
637
+ INFO:hf-to-gguf:blk.33.ssm_a, torch.bfloat16 --> F32, shape = {32}
638
+ INFO:hf-to-gguf:blk.33.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
639
+ INFO:hf-to-gguf:blk.33.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
640
+ INFO:hf-to-gguf:blk.33.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
641
+ INFO:hf-to-gguf:blk.33.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
642
+ INFO:hf-to-gguf:blk.33.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
643
+ INFO:hf-to-gguf:blk.33.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
644
+ INFO:hf-to-gguf:blk.33.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
645
+ INFO:hf-to-gguf:blk.33.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
646
+ INFO:hf-to-gguf:blk.33.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
647
+ INFO:hf-to-gguf:blk.33.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
648
+ INFO:hf-to-gguf:blk.33.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
649
+ INFO:hf-to-gguf:blk.33.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
650
+ INFO:hf-to-gguf:blk.33.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
651
+ INFO:hf-to-gguf:blk.33.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
652
+ INFO:hf-to-gguf:blk.33.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
653
+ INFO:hf-to-gguf:blk.33.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
654
+ INFO:hf-to-gguf:blk.33.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
655
+ INFO:hf-to-gguf:blk.34.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
656
+ INFO:hf-to-gguf:blk.34.ssm_a, torch.bfloat16 --> F32, shape = {32}
657
+ INFO:hf-to-gguf:blk.34.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
658
+ INFO:hf-to-gguf:blk.34.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
659
+ INFO:hf-to-gguf:blk.34.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
660
+ INFO:hf-to-gguf:blk.34.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
661
+ INFO:hf-to-gguf:blk.34.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
662
+ INFO:hf-to-gguf:blk.34.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
663
+ INFO:hf-to-gguf:blk.34.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
664
+ INFO:hf-to-gguf:blk.34.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
665
+ INFO:hf-to-gguf:blk.34.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
666
+ INFO:hf-to-gguf:blk.34.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
667
+ INFO:hf-to-gguf:blk.34.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
668
+ INFO:hf-to-gguf:blk.34.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
669
+ INFO:hf-to-gguf:blk.34.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
670
+ INFO:hf-to-gguf:blk.34.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
671
+ INFO:hf-to-gguf:blk.34.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
672
+ INFO:hf-to-gguf:blk.34.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
673
+ INFO:hf-to-gguf:blk.34.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
674
+ INFO:hf-to-gguf:blk.35.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
675
+ INFO:hf-to-gguf:blk.35.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
676
+ INFO:hf-to-gguf:blk.35.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
677
+ INFO:hf-to-gguf:blk.35.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
678
+ INFO:hf-to-gguf:blk.35.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
679
+ INFO:hf-to-gguf:blk.35.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
680
+ INFO:hf-to-gguf:blk.35.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
681
+ INFO:hf-to-gguf:blk.35.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
682
+ INFO:hf-to-gguf:blk.35.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
683
+ INFO:hf-to-gguf:blk.35.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
684
+ INFO:hf-to-gguf:blk.35.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
685
+ INFO:hf-to-gguf:blk.35.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
686
+ INFO:hf-to-gguf:blk.35.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
687
+ INFO:hf-to-gguf:blk.35.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
688
+ INFO:hf-to-gguf:blk.35.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
689
+ INFO:hf-to-gguf:blk.35.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
690
+ INFO:hf-to-gguf:blk.36.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
691
+ INFO:hf-to-gguf:blk.36.ssm_a, torch.bfloat16 --> F32, shape = {32}
692
+ INFO:hf-to-gguf:blk.36.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
693
+ INFO:hf-to-gguf:blk.36.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
694
+ INFO:hf-to-gguf:blk.36.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
695
+ INFO:hf-to-gguf:blk.36.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
696
+ INFO:hf-to-gguf:blk.36.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
697
+ INFO:hf-to-gguf:blk.36.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
698
+ INFO:hf-to-gguf:blk.36.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
699
+ INFO:hf-to-gguf:blk.36.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
700
+ INFO:hf-to-gguf:blk.36.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
701
+ INFO:hf-to-gguf:blk.36.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
702
+ INFO:hf-to-gguf:blk.36.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
703
+ INFO:hf-to-gguf:blk.36.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
704
+ INFO:hf-to-gguf:blk.36.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
705
+ INFO:hf-to-gguf:blk.36.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
706
+ INFO:hf-to-gguf:blk.36.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
707
+ INFO:hf-to-gguf:blk.36.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
708
+ INFO:hf-to-gguf:blk.36.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
709
+ INFO:hf-to-gguf:blk.37.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
710
+ INFO:hf-to-gguf:blk.37.ssm_a, torch.bfloat16 --> F32, shape = {32}
711
+ INFO:hf-to-gguf:blk.37.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
712
+ INFO:hf-to-gguf:blk.37.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
713
+ INFO:hf-to-gguf:blk.37.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
714
+ INFO:hf-to-gguf:blk.37.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
715
+ INFO:hf-to-gguf:blk.37.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
716
+ INFO:hf-to-gguf:blk.37.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
717
+ INFO:hf-to-gguf:blk.37.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
718
+ INFO:hf-to-gguf:blk.37.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
719
+ INFO:hf-to-gguf:blk.37.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
720
+ INFO:hf-to-gguf:blk.37.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
721
+ INFO:hf-to-gguf:blk.37.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
722
+ INFO:hf-to-gguf:blk.37.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
723
+ INFO:hf-to-gguf:blk.37.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
724
+ INFO:hf-to-gguf:blk.37.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
725
+ INFO:hf-to-gguf:blk.37.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
726
+ INFO:hf-to-gguf:blk.37.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
727
+ INFO:hf-to-gguf:blk.37.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
728
+ INFO:hf-to-gguf:blk.38.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
729
+ INFO:hf-to-gguf:blk.38.ssm_a, torch.bfloat16 --> F32, shape = {32}
730
+ INFO:hf-to-gguf:blk.38.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
731
+ INFO:hf-to-gguf:blk.38.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
732
+ INFO:hf-to-gguf:blk.38.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
733
+ INFO:hf-to-gguf:blk.38.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
734
+ INFO:hf-to-gguf:blk.38.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
735
+ INFO:hf-to-gguf:blk.38.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
736
+ INFO:hf-to-gguf:blk.38.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
737
+ INFO:hf-to-gguf:blk.38.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
738
+ INFO:hf-to-gguf:blk.38.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
739
+ INFO:hf-to-gguf:blk.38.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
740
+ INFO:hf-to-gguf:blk.38.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
741
+ INFO:hf-to-gguf:blk.38.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
742
+ INFO:hf-to-gguf:blk.38.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
743
+ INFO:hf-to-gguf:blk.38.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
744
+ INFO:hf-to-gguf:blk.38.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
745
+ INFO:hf-to-gguf:blk.38.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
746
+ INFO:hf-to-gguf:blk.38.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
747
+ INFO:hf-to-gguf:blk.39.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
748
+ INFO:hf-to-gguf:blk.39.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
749
+ INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
750
+ INFO:hf-to-gguf:blk.39.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
751
+ INFO:hf-to-gguf:blk.39.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
752
+ INFO:hf-to-gguf:blk.39.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
753
+ INFO:hf-to-gguf:blk.39.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
754
+ INFO:hf-to-gguf:blk.39.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
755
+ INFO:hf-to-gguf:blk.39.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
756
+ INFO:hf-to-gguf:blk.39.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
757
+ INFO:hf-to-gguf:blk.39.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
758
+ INFO:hf-to-gguf:blk.39.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
759
+ INFO:hf-to-gguf:blk.39.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
760
+ INFO:hf-to-gguf:blk.39.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
761
+ INFO:hf-to-gguf:blk.39.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
762
+ INFO:hf-to-gguf:blk.39.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
763
+ INFO:hf-to-gguf:blk.39.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
764
+ INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {2048}
765
+ INFO:hf-to-gguf:Set meta model
766
+ INFO:hf-to-gguf:Set model parameters
767
+ INFO:hf-to-gguf:gguf: context length = 262144
768
+ INFO:hf-to-gguf:gguf: embedding length = 2048
769
+ INFO:hf-to-gguf:gguf: head count = 16
770
+ INFO:hf-to-gguf:gguf: key-value head count = 2
771
+ WARNING:hf-to-gguf:Unknown RoPE type: default
772
+ INFO:hf-to-gguf:gguf: rope scaling type = NONE
773
+ INFO:hf-to-gguf:gguf: mrope sections: [11, 11, 10, 0]
774
+ INFO:hf-to-gguf:gguf: rope theta = 10000000
775
+ INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
776
+ INFO:hf-to-gguf:gguf: expert count = 256
777
+ INFO:hf-to-gguf:gguf: experts used count = 8
778
+ INFO:hf-to-gguf:gguf: file type = 32
779
+ INFO:hf-to-gguf:gguf: expert feed forward length = 512
780
+ INFO:hf-to-gguf:gguf: expert shared feed forward length = 512
781
+ INFO:hf-to-gguf:Set model quantization version
782
+ INFO:hf-to-gguf:Set model tokenizer
783
+ INFO:gguf.vocab:Adding 247587 merge(s).
784
+ INFO:gguf.vocab:Setting special token type eos to 248046
785
+ INFO:gguf.vocab:Setting special token type pad to 248044
786
+ INFO:gguf.vocab:Setting special token type bos to 248044
787
+ INFO:gguf.vocab:Setting add_bos_token to False
788
+ INFO:gguf.vocab:Setting chat_template to {%- set image_count = namespace(value=0) %}
789
+ {%- set video_count = namespace(value=0) %}
790
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
791
+ {%- if content is string %}
792
+ {{- content }}
793
+ {%- elif content is iterable and content is not mapping %}
794
+ {%- for item in content %}
795
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
796
+ {%- if is_system_content %}
797
+ {{- raise_exception('System message cannot contain images.') }}
798
+ {%- endif %}
799
+ {%- if do_vision_count %}
800
+ {%- set image_count.value = image_count.value + 1 %}
801
+ {%- endif %}
802
+ {%- if add_vision_id %}
803
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
804
+ {%- endif %}
805
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
806
+ {%- elif 'video' in item or item.type == 'video' %}
807
+ {%- if is_system_content %}
808
+ {{- raise_exception('System message cannot contain videos.') }}
809
+ {%- endif %}
810
+ {%- if do_vision_count %}
811
+ {%- set video_count.value = video_count.value + 1 %}
812
+ {%- endif %}
813
+ {%- if add_vision_id %}
814
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
815
+ {%- endif %}
816
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
817
+ {%- elif 'text' in item %}
818
+ {{- item.text }}
819
+ {%- else %}
820
+ {{- raise_exception('Unexpected item type in content.') }}
821
+ {%- endif %}
822
+ {%- endfor %}
823
+ {%- elif content is none or content is undefined %}
824
+ {{- '' }}
825
+ {%- else %}
826
+ {{- raise_exception('Unexpected content type.') }}
827
+ {%- endif %}
828
+ {%- endmacro %}
829
+ {%- if not messages %}
830
+ {{- raise_exception('No messages provided.') }}
831
+ {%- endif %}
832
+ {%- if tools and tools is iterable and tools is not mapping %}
833
+ {{- '<|im_start|>system\n' }}
834
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
835
+ {%- for tool in tools %}
836
+ {{- "\n" }}
837
+ {{- tool | tojson }}
838
+ {%- endfor %}
839
+ {{- "\n</tools>" }}
840
+ {{- '\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>' }}
841
+ {%- if messages[0].role == 'system' %}
842
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
843
+ {%- if content %}
844
+ {{- '\n\n' + content }}
845
+ {%- endif %}
846
+ {%- endif %}
847
+ {{- '<|im_end|>\n' }}
848
+ {%- else %}
849
+ {%- if messages[0].role == 'system' %}
850
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
851
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
852
+ {%- endif %}
853
+ {%- endif %}
854
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
855
+ {%- for message in messages[::-1] %}
856
+ {%- set index = (messages|length - 1) - loop.index0 %}
857
+ {%- if ns.multi_step_tool and message.role == "user" %}
858
+ {%- set content = render_content(message.content, false)|trim %}
859
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
860
+ {%- set ns.multi_step_tool = false %}
861
+ {%- set ns.last_query_index = index %}
862
+ {%- endif %}
863
+ {%- endif %}
864
+ {%- endfor %}
865
+ {%- if ns.multi_step_tool %}
866
+ {{- raise_exception('No user query found in messages.') }}
867
+ {%- endif %}
868
+ {%- for message in messages %}
869
+ {%- set content = render_content(message.content, true)|trim %}
870
+ {%- if message.role == "system" %}
871
+ {%- if not loop.first %}
872
+ {{- raise_exception('System message must be at the beginning.') }}
873
+ {%- endif %}
874
+ {%- elif message.role == "user" %}
875
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
876
+ {%- elif message.role == "assistant" %}
877
+ {%- set reasoning_content = '' %}
878
+ {%- if message.reasoning_content is string %}
879
+ {%- set reasoning_content = message.reasoning_content %}
880
+ {%- else %}
881
+ {%- if '</think>' in content %}
882
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
883
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
884
+ {%- endif %}
885
+ {%- endif %}
886
+ {%- set reasoning_content = reasoning_content|trim %}
887
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
888
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
889
+ {%- else %}
890
+ {{- '<|im_start|>' + message.role + '\n' + content }}
891
+ {%- endif %}
892
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
893
+ {%- for tool_call in message.tool_calls %}
894
+ {%- if tool_call.function is defined %}
895
+ {%- set tool_call = tool_call.function %}
896
+ {%- endif %}
897
+ {%- if loop.first %}
898
+ {%- if content|trim %}
899
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
900
+ {%- else %}
901
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
902
+ {%- endif %}
903
+ {%- else %}
904
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
905
+ {%- endif %}
906
+ {%- if tool_call.arguments is defined %}
907
+ {%- for args_name, args_value in tool_call.arguments|items %}
908
+ {{- '<parameter=' + args_name + '>\n' }}
909
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
910
+ {{- args_value }}
911
+ {{- '\n</parameter>\n' }}
912
+ {%- endfor %}
913
+ {%- endif %}
914
+ {{- '</function>\n</tool_call>' }}
915
+ {%- endfor %}
916
+ {%- endif %}
917
+ {{- '<|im_end|>\n' }}
918
+ {%- elif message.role == "tool" %}
919
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
920
+ {{- '<|im_start|>user' }}
921
+ {%- endif %}
922
+ {{- '\n<tool_response>\n' }}
923
+ {{- content }}
924
+ {{- '\n</tool_response>' }}
925
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
926
+ {{- '<|im_end|>\n' }}
927
+ {%- elif loop.last %}
928
+ {{- '<|im_end|>\n' }}
929
+ {%- endif %}
930
+ {%- else %}
931
+ {{- raise_exception('Unexpected message role.') }}
932
+ {%- endif %}
933
+ {%- endfor %}
934
+ {%- if add_generation_prompt %}
935
+ {{- '<|im_start|>assistant\n' }}
936
+ {%- if enable_thinking is defined and enable_thinking is false %}
937
+ {{- '<think>\n\n</think>\n\n' }}
938
+ {%- else %}
939
+ {{- '<think>\n' }}
940
+ {%- endif %}
941
+ {%- endif %}
942
+ INFO:gguf.gguf_writer:Writing the following files:
943
+ INFO:gguf.gguf_writer:/tmp/q_quant_work/main.bf16.gguf: n_tensors = 733, total_size = 69.4G
944
+
945
+ INFO:hf-to-gguf:Model successfully exported to /tmp/q_quant_work/main.bf16.gguf
convert_mmproj.log ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ INFO:hf-to-gguf:Loading model: source_model
2
+ INFO:hf-to-gguf:Model architecture: Qwen3_5MoeForConditionalGeneration
3
+ INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
4
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00026.safetensors'
5
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00026.safetensors'
6
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00026.safetensors'
7
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00026.safetensors'
8
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00026.safetensors'
9
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00026.safetensors'
10
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00026.safetensors'
11
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00026.safetensors'
12
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00026.safetensors'
13
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00026.safetensors'
14
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00026.safetensors'
15
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00026.safetensors'
16
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00026.safetensors'
17
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00026.safetensors'
18
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00026.safetensors'
19
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00026.safetensors'
20
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00026.safetensors'
21
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00026.safetensors'
22
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00026.safetensors'
23
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00026.safetensors'
24
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00026.safetensors'
25
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00026.safetensors'
26
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00026.safetensors'
27
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00026.safetensors'
28
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00026.safetensors'
29
+ INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00026.safetensors'
30
+ INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
31
+ INFO:hf-to-gguf:Exporting model...
32
+ INFO:hf-to-gguf:v.blk.0.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
33
+ INFO:hf-to-gguf:v.blk.0.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
34
+ INFO:hf-to-gguf:v.blk.1.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
35
+ INFO:hf-to-gguf:v.blk.1.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
36
+ INFO:hf-to-gguf:v.blk.10.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
37
+ INFO:hf-to-gguf:v.blk.10.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
38
+ INFO:hf-to-gguf:v.blk.11.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
39
+ INFO:hf-to-gguf:v.blk.11.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
40
+ INFO:hf-to-gguf:v.blk.12.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
41
+ INFO:hf-to-gguf:v.blk.12.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
42
+ INFO:hf-to-gguf:mm.0.weight, torch.bfloat16 --> F16, shape = {4608, 4608}
43
+ INFO:hf-to-gguf:mm.2.weight, torch.bfloat16 --> F16, shape = {4608, 2048}
44
+ INFO:hf-to-gguf:v.blk.0.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
45
+ INFO:hf-to-gguf:v.blk.0.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
46
+ INFO:hf-to-gguf:v.blk.0.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
47
+ INFO:hf-to-gguf:v.blk.0.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
48
+ INFO:hf-to-gguf:v.blk.0.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
49
+ INFO:hf-to-gguf:v.blk.0.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
50
+ INFO:hf-to-gguf:v.blk.0.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
51
+ INFO:hf-to-gguf:v.blk.0.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
52
+ INFO:hf-to-gguf:v.blk.0.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
53
+ INFO:hf-to-gguf:v.blk.0.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
54
+ INFO:hf-to-gguf:v.blk.1.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
55
+ INFO:hf-to-gguf:v.blk.1.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
56
+ INFO:hf-to-gguf:v.blk.1.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
57
+ INFO:hf-to-gguf:v.blk.1.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
58
+ INFO:hf-to-gguf:v.blk.1.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
59
+ INFO:hf-to-gguf:v.blk.1.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
60
+ INFO:hf-to-gguf:v.blk.1.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
61
+ INFO:hf-to-gguf:v.blk.1.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
62
+ INFO:hf-to-gguf:v.blk.1.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
63
+ INFO:hf-to-gguf:v.blk.1.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
64
+ INFO:hf-to-gguf:v.blk.10.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
65
+ INFO:hf-to-gguf:v.blk.10.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
66
+ INFO:hf-to-gguf:v.blk.10.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
67
+ INFO:hf-to-gguf:v.blk.10.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
68
+ INFO:hf-to-gguf:v.blk.10.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
69
+ INFO:hf-to-gguf:v.blk.10.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
70
+ INFO:hf-to-gguf:v.blk.10.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
71
+ INFO:hf-to-gguf:v.blk.10.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
72
+ INFO:hf-to-gguf:v.blk.10.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
73
+ INFO:hf-to-gguf:v.blk.10.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
74
+ INFO:hf-to-gguf:v.blk.11.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
75
+ INFO:hf-to-gguf:v.blk.11.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
76
+ INFO:hf-to-gguf:v.blk.11.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
77
+ INFO:hf-to-gguf:v.blk.11.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
78
+ INFO:hf-to-gguf:v.blk.11.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
79
+ INFO:hf-to-gguf:v.blk.11.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
80
+ INFO:hf-to-gguf:v.blk.11.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
81
+ INFO:hf-to-gguf:v.blk.11.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
82
+ INFO:hf-to-gguf:v.blk.11.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
83
+ INFO:hf-to-gguf:v.blk.11.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
84
+ INFO:hf-to-gguf:v.blk.12.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
85
+ INFO:hf-to-gguf:v.blk.12.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
86
+ INFO:hf-to-gguf:v.blk.12.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
87
+ INFO:hf-to-gguf:v.blk.12.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
88
+ INFO:hf-to-gguf:v.blk.12.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
89
+ INFO:hf-to-gguf:v.blk.12.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
90
+ INFO:hf-to-gguf:v.blk.12.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
91
+ INFO:hf-to-gguf:v.blk.12.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
92
+ INFO:hf-to-gguf:v.blk.12.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
93
+ INFO:hf-to-gguf:v.blk.12.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
94
+ INFO:hf-to-gguf:v.blk.13.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
95
+ INFO:hf-to-gguf:v.blk.13.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
96
+ INFO:hf-to-gguf:v.blk.13.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
97
+ INFO:hf-to-gguf:v.blk.13.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
98
+ INFO:hf-to-gguf:v.blk.13.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
99
+ INFO:hf-to-gguf:v.blk.13.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
100
+ INFO:hf-to-gguf:v.blk.13.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
101
+ INFO:hf-to-gguf:v.blk.13.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
102
+ INFO:hf-to-gguf:v.blk.13.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
103
+ INFO:hf-to-gguf:v.blk.13.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
104
+ INFO:hf-to-gguf:v.blk.13.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
105
+ INFO:hf-to-gguf:v.blk.13.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
106
+ INFO:hf-to-gguf:v.blk.14.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
107
+ INFO:hf-to-gguf:v.blk.14.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
108
+ INFO:hf-to-gguf:v.blk.14.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
109
+ INFO:hf-to-gguf:v.blk.14.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
110
+ INFO:hf-to-gguf:v.blk.14.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
111
+ INFO:hf-to-gguf:v.blk.14.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
112
+ INFO:hf-to-gguf:v.blk.14.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
113
+ INFO:hf-to-gguf:v.blk.14.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
114
+ INFO:hf-to-gguf:v.blk.14.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
115
+ INFO:hf-to-gguf:v.blk.14.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
116
+ INFO:hf-to-gguf:v.blk.14.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
117
+ INFO:hf-to-gguf:v.blk.14.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
118
+ INFO:hf-to-gguf:v.blk.15.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
119
+ INFO:hf-to-gguf:v.blk.15.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
120
+ INFO:hf-to-gguf:v.blk.15.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
121
+ INFO:hf-to-gguf:v.blk.15.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
122
+ INFO:hf-to-gguf:v.blk.15.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
123
+ INFO:hf-to-gguf:v.blk.15.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
124
+ INFO:hf-to-gguf:v.blk.15.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
125
+ INFO:hf-to-gguf:v.blk.15.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
126
+ INFO:hf-to-gguf:v.blk.15.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
127
+ INFO:hf-to-gguf:v.blk.15.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
128
+ INFO:hf-to-gguf:v.blk.15.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
129
+ INFO:hf-to-gguf:v.blk.15.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
130
+ INFO:hf-to-gguf:v.blk.16.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
131
+ INFO:hf-to-gguf:v.blk.16.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
132
+ INFO:hf-to-gguf:v.blk.16.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
133
+ INFO:hf-to-gguf:v.blk.16.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
134
+ INFO:hf-to-gguf:v.blk.16.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
135
+ INFO:hf-to-gguf:v.blk.16.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
136
+ INFO:hf-to-gguf:v.blk.16.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
137
+ INFO:hf-to-gguf:v.blk.16.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
138
+ INFO:hf-to-gguf:v.blk.16.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
139
+ INFO:hf-to-gguf:v.blk.16.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
140
+ INFO:hf-to-gguf:v.blk.16.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
141
+ INFO:hf-to-gguf:v.blk.16.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
142
+ INFO:hf-to-gguf:v.blk.17.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
143
+ INFO:hf-to-gguf:v.blk.17.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
144
+ INFO:hf-to-gguf:v.blk.17.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
145
+ INFO:hf-to-gguf:v.blk.17.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
146
+ INFO:hf-to-gguf:v.blk.17.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
147
+ INFO:hf-to-gguf:v.blk.17.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
148
+ INFO:hf-to-gguf:v.blk.17.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
149
+ INFO:hf-to-gguf:v.blk.17.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
150
+ INFO:hf-to-gguf:v.blk.17.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
151
+ INFO:hf-to-gguf:v.blk.17.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
152
+ INFO:hf-to-gguf:v.blk.17.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
153
+ INFO:hf-to-gguf:v.blk.17.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
154
+ INFO:hf-to-gguf:v.blk.18.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
155
+ INFO:hf-to-gguf:v.blk.18.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
156
+ INFO:hf-to-gguf:v.blk.18.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
157
+ INFO:hf-to-gguf:v.blk.18.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
158
+ INFO:hf-to-gguf:v.blk.18.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
159
+ INFO:hf-to-gguf:v.blk.18.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
160
+ INFO:hf-to-gguf:v.blk.18.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
161
+ INFO:hf-to-gguf:v.blk.18.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
162
+ INFO:hf-to-gguf:v.blk.18.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
163
+ INFO:hf-to-gguf:v.blk.18.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
164
+ INFO:hf-to-gguf:v.blk.18.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
165
+ INFO:hf-to-gguf:v.blk.18.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
166
+ INFO:hf-to-gguf:v.blk.19.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
167
+ INFO:hf-to-gguf:v.blk.19.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
168
+ INFO:hf-to-gguf:v.blk.19.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
169
+ INFO:hf-to-gguf:v.blk.19.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
170
+ INFO:hf-to-gguf:v.blk.19.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
171
+ INFO:hf-to-gguf:v.blk.19.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
172
+ INFO:hf-to-gguf:v.blk.19.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
173
+ INFO:hf-to-gguf:v.blk.19.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
174
+ INFO:hf-to-gguf:v.blk.19.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
175
+ INFO:hf-to-gguf:v.blk.19.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
176
+ INFO:hf-to-gguf:v.blk.19.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
177
+ INFO:hf-to-gguf:v.blk.19.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
178
+ INFO:hf-to-gguf:v.blk.2.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
179
+ INFO:hf-to-gguf:v.blk.2.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
180
+ INFO:hf-to-gguf:v.blk.2.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
181
+ INFO:hf-to-gguf:v.blk.2.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
182
+ INFO:hf-to-gguf:v.blk.2.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
183
+ INFO:hf-to-gguf:v.blk.2.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
184
+ INFO:hf-to-gguf:v.blk.2.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
185
+ INFO:hf-to-gguf:v.blk.2.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
186
+ INFO:hf-to-gguf:v.blk.2.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
187
+ INFO:hf-to-gguf:v.blk.2.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
188
+ INFO:hf-to-gguf:v.blk.2.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
189
+ INFO:hf-to-gguf:v.blk.2.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
190
+ INFO:hf-to-gguf:v.blk.20.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
191
+ INFO:hf-to-gguf:v.blk.20.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
192
+ INFO:hf-to-gguf:v.blk.20.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
193
+ INFO:hf-to-gguf:v.blk.20.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
194
+ INFO:hf-to-gguf:v.blk.20.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
195
+ INFO:hf-to-gguf:v.blk.20.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
196
+ INFO:hf-to-gguf:v.blk.20.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
197
+ INFO:hf-to-gguf:v.blk.20.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
198
+ INFO:hf-to-gguf:v.blk.20.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
199
+ INFO:hf-to-gguf:v.blk.20.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
200
+ INFO:hf-to-gguf:v.blk.20.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
201
+ INFO:hf-to-gguf:v.blk.20.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
202
+ INFO:hf-to-gguf:v.blk.21.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
203
+ INFO:hf-to-gguf:v.blk.21.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
204
+ INFO:hf-to-gguf:v.blk.21.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
205
+ INFO:hf-to-gguf:v.blk.21.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
206
+ INFO:hf-to-gguf:v.blk.21.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
207
+ INFO:hf-to-gguf:v.blk.21.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
208
+ INFO:hf-to-gguf:v.blk.21.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
209
+ INFO:hf-to-gguf:v.blk.21.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
210
+ INFO:hf-to-gguf:v.blk.21.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
211
+ INFO:hf-to-gguf:v.blk.21.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
212
+ INFO:hf-to-gguf:v.blk.21.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
213
+ INFO:hf-to-gguf:v.blk.21.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
214
+ INFO:hf-to-gguf:v.blk.22.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
215
+ INFO:hf-to-gguf:v.blk.22.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
216
+ INFO:hf-to-gguf:v.blk.22.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
217
+ INFO:hf-to-gguf:v.blk.22.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
218
+ INFO:hf-to-gguf:v.blk.22.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
219
+ INFO:hf-to-gguf:v.blk.22.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
220
+ INFO:hf-to-gguf:v.blk.22.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
221
+ INFO:hf-to-gguf:v.blk.22.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
222
+ INFO:hf-to-gguf:v.blk.22.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
223
+ INFO:hf-to-gguf:v.blk.22.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
224
+ INFO:hf-to-gguf:v.blk.22.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
225
+ INFO:hf-to-gguf:v.blk.22.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
226
+ INFO:hf-to-gguf:v.blk.23.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
227
+ INFO:hf-to-gguf:v.blk.23.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
228
+ INFO:hf-to-gguf:v.blk.23.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
229
+ INFO:hf-to-gguf:v.blk.23.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
230
+ INFO:hf-to-gguf:v.blk.23.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
231
+ INFO:hf-to-gguf:v.blk.23.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
232
+ INFO:hf-to-gguf:v.blk.23.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
233
+ INFO:hf-to-gguf:v.blk.23.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
234
+ INFO:hf-to-gguf:v.blk.23.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
235
+ INFO:hf-to-gguf:v.blk.23.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
236
+ INFO:hf-to-gguf:v.blk.23.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
237
+ INFO:hf-to-gguf:v.blk.23.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
238
+ INFO:hf-to-gguf:v.blk.24.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
239
+ INFO:hf-to-gguf:v.blk.24.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
240
+ INFO:hf-to-gguf:v.blk.24.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
241
+ INFO:hf-to-gguf:v.blk.24.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
242
+ INFO:hf-to-gguf:v.blk.24.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
243
+ INFO:hf-to-gguf:v.blk.24.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
244
+ INFO:hf-to-gguf:v.blk.24.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
245
+ INFO:hf-to-gguf:v.blk.24.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
246
+ INFO:hf-to-gguf:v.blk.24.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
247
+ INFO:hf-to-gguf:v.blk.24.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
248
+ INFO:hf-to-gguf:v.blk.24.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
249
+ INFO:hf-to-gguf:v.blk.24.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
250
+ INFO:hf-to-gguf:v.blk.25.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
251
+ INFO:hf-to-gguf:v.blk.25.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
252
+ INFO:hf-to-gguf:v.blk.25.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
253
+ INFO:hf-to-gguf:v.blk.25.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
254
+ INFO:hf-to-gguf:v.blk.25.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
255
+ INFO:hf-to-gguf:v.blk.25.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
256
+ INFO:hf-to-gguf:v.blk.25.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
257
+ INFO:hf-to-gguf:v.blk.25.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
258
+ INFO:hf-to-gguf:v.blk.25.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
259
+ INFO:hf-to-gguf:v.blk.25.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
260
+ INFO:hf-to-gguf:v.blk.25.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
261
+ INFO:hf-to-gguf:v.blk.25.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
262
+ INFO:hf-to-gguf:v.blk.26.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
263
+ INFO:hf-to-gguf:v.blk.26.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
264
+ INFO:hf-to-gguf:v.blk.26.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
265
+ INFO:hf-to-gguf:v.blk.26.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
266
+ INFO:hf-to-gguf:v.blk.26.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
267
+ INFO:hf-to-gguf:v.blk.26.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
268
+ INFO:hf-to-gguf:v.blk.26.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
269
+ INFO:hf-to-gguf:v.blk.26.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
270
+ INFO:hf-to-gguf:v.blk.26.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
271
+ INFO:hf-to-gguf:v.blk.26.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
272
+ INFO:hf-to-gguf:v.blk.26.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
273
+ INFO:hf-to-gguf:v.blk.26.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
274
+ INFO:hf-to-gguf:v.blk.3.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
275
+ INFO:hf-to-gguf:v.blk.3.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
276
+ INFO:hf-to-gguf:v.blk.3.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
277
+ INFO:hf-to-gguf:v.blk.3.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
278
+ INFO:hf-to-gguf:v.blk.3.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
279
+ INFO:hf-to-gguf:v.blk.3.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
280
+ INFO:hf-to-gguf:v.blk.3.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
281
+ INFO:hf-to-gguf:v.blk.3.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
282
+ INFO:hf-to-gguf:v.blk.3.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
283
+ INFO:hf-to-gguf:v.blk.3.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
284
+ INFO:hf-to-gguf:v.blk.3.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
285
+ INFO:hf-to-gguf:v.blk.3.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
286
+ INFO:hf-to-gguf:v.blk.4.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
287
+ INFO:hf-to-gguf:v.blk.4.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
288
+ INFO:hf-to-gguf:v.blk.4.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
289
+ INFO:hf-to-gguf:v.blk.4.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
290
+ INFO:hf-to-gguf:v.blk.4.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
291
+ INFO:hf-to-gguf:v.blk.4.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
292
+ INFO:hf-to-gguf:v.blk.4.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
293
+ INFO:hf-to-gguf:v.blk.4.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
294
+ INFO:hf-to-gguf:v.blk.4.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
295
+ INFO:hf-to-gguf:v.blk.4.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
296
+ INFO:hf-to-gguf:v.blk.4.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
297
+ INFO:hf-to-gguf:v.blk.4.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
298
+ INFO:hf-to-gguf:v.blk.5.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
299
+ INFO:hf-to-gguf:v.blk.5.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
300
+ INFO:hf-to-gguf:v.blk.5.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
301
+ INFO:hf-to-gguf:v.blk.5.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
302
+ INFO:hf-to-gguf:v.blk.5.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
303
+ INFO:hf-to-gguf:v.blk.5.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
304
+ INFO:hf-to-gguf:v.blk.5.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
305
+ INFO:hf-to-gguf:v.blk.5.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
306
+ INFO:hf-to-gguf:v.blk.5.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
307
+ INFO:hf-to-gguf:v.blk.5.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
308
+ INFO:hf-to-gguf:v.blk.5.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
309
+ INFO:hf-to-gguf:v.blk.5.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
310
+ INFO:hf-to-gguf:v.blk.6.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
311
+ INFO:hf-to-gguf:v.blk.6.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
312
+ INFO:hf-to-gguf:v.blk.6.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
313
+ INFO:hf-to-gguf:v.blk.6.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
314
+ INFO:hf-to-gguf:v.blk.6.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
315
+ INFO:hf-to-gguf:v.blk.6.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
316
+ INFO:hf-to-gguf:v.blk.6.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
317
+ INFO:hf-to-gguf:v.blk.6.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
318
+ INFO:hf-to-gguf:v.blk.6.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
319
+ INFO:hf-to-gguf:v.blk.6.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
320
+ INFO:hf-to-gguf:v.blk.6.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
321
+ INFO:hf-to-gguf:v.blk.6.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
322
+ INFO:hf-to-gguf:v.blk.7.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
323
+ INFO:hf-to-gguf:v.blk.7.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
324
+ INFO:hf-to-gguf:v.blk.7.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
325
+ INFO:hf-to-gguf:v.blk.7.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
326
+ INFO:hf-to-gguf:v.blk.7.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
327
+ INFO:hf-to-gguf:v.blk.7.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
328
+ INFO:hf-to-gguf:v.blk.7.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
329
+ INFO:hf-to-gguf:v.blk.7.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
330
+ INFO:hf-to-gguf:v.blk.7.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
331
+ INFO:hf-to-gguf:v.blk.7.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
332
+ INFO:hf-to-gguf:v.blk.7.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
333
+ INFO:hf-to-gguf:v.blk.7.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
334
+ INFO:hf-to-gguf:v.blk.8.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
335
+ INFO:hf-to-gguf:v.blk.8.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
336
+ INFO:hf-to-gguf:v.blk.8.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
337
+ INFO:hf-to-gguf:v.blk.8.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
338
+ INFO:hf-to-gguf:v.blk.8.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
339
+ INFO:hf-to-gguf:v.blk.8.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
340
+ INFO:hf-to-gguf:v.blk.8.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
341
+ INFO:hf-to-gguf:v.blk.8.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
342
+ INFO:hf-to-gguf:v.blk.8.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
343
+ INFO:hf-to-gguf:v.blk.8.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
344
+ INFO:hf-to-gguf:v.blk.8.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
345
+ INFO:hf-to-gguf:v.blk.8.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
346
+ INFO:hf-to-gguf:v.blk.9.attn_out.bias, torch.bfloat16 --> F32, shape = {1152}
347
+ INFO:hf-to-gguf:v.blk.9.attn_out.weight, torch.bfloat16 --> F16, shape = {1152, 1152}
348
+ INFO:hf-to-gguf:v.blk.9.attn_qkv.bias, torch.bfloat16 --> F32, shape = {3456}
349
+ INFO:hf-to-gguf:v.blk.9.attn_qkv.weight, torch.bfloat16 --> F16, shape = {1152, 3456}
350
+ INFO:hf-to-gguf:v.blk.9.ffn_up.bias, torch.bfloat16 --> F32, shape = {4304}
351
+ INFO:hf-to-gguf:v.blk.9.ffn_up.weight, torch.bfloat16 --> F16, shape = {1152, 4304}
352
+ INFO:hf-to-gguf:v.blk.9.ffn_down.bias, torch.bfloat16 --> F32, shape = {1152}
353
+ INFO:hf-to-gguf:v.blk.9.ffn_down.weight, torch.bfloat16 --> F16, shape = {4304, 1152}
354
+ INFO:hf-to-gguf:v.blk.9.ln1.bias, torch.bfloat16 --> F32, shape = {1152}
355
+ INFO:hf-to-gguf:v.blk.9.ln1.weight, torch.bfloat16 --> F32, shape = {1152}
356
+ INFO:hf-to-gguf:v.blk.9.ln2.bias, torch.bfloat16 --> F32, shape = {1152}
357
+ INFO:hf-to-gguf:v.blk.9.ln2.weight, torch.bfloat16 --> F32, shape = {1152}
358
+ INFO:hf-to-gguf:mm.0.bias, torch.bfloat16 --> F32, shape = {4608}
359
+ INFO:hf-to-gguf:mm.2.bias, torch.bfloat16 --> F32, shape = {2048}
360
+ INFO:hf-to-gguf:v.post_ln.bias, torch.bfloat16 --> F32, shape = {1152}
361
+ INFO:hf-to-gguf:v.post_ln.weight, torch.bfloat16 --> F32, shape = {1152}
362
+ INFO:hf-to-gguf:v.patch_embd.bias, torch.bfloat16 --> F32, shape = {1152}
363
+ INFO:hf-to-gguf:v.patch_embd.weight, torch.bfloat16 --> F16, shape = {16, 16, 3, 1152}
364
+ INFO:hf-to-gguf:v.patch_embd.weight.1, torch.bfloat16 --> F16, shape = {16, 16, 3, 1152}
365
+ INFO:hf-to-gguf:v.position_embd.weight, torch.bfloat16 --> F32, shape = {1152, 2304}
366
+ INFO:hf-to-gguf:Set meta model
367
+ INFO:hf-to-gguf:Set model parameters
368
+ INFO:hf-to-gguf:Set model quantization version
369
+ INFO:gguf.gguf_writer:Writing the following files:
370
+ INFO:gguf.gguf_writer:/tmp/q_quant_work/mmproj.f16.gguf: n_tensors = 334, total_size = 899.3M
371
+
372
+ INFO:hf-to-gguf:Model successfully exported to /tmp/q_quant_work/mmproj.f16.gguf
imatrix.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac1f482a56d7d08ac7dd6c6935fe3bfc1662f5586d645d5634f7a29ae3f4255
3
+ size 192232256
imatrix.log ADDED
The diff for this file is too large to render. See raw diff
 
main.bf16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4d3e53e2ec5e036e21cfe8fe196376d5f409ec4fd35bf50ee629a047f4db2c
3
+ size 69376637024
mmproj.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4baaa5ba48e097ed383aac6777677a3f3fbe0fa96d37174856f51c37028be70
3
+ size 899282976
q4_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bfe5d1bd8e0cb6d737bc7056aff79443c77a99aa2391b7ccef2c5e1ee7db815
3
+ size 21297870912
quantize_q4_k_m.log ADDED
The diff for this file is too large to render. See raw diff