Hugging Face's logo

QuantTrio
/
KAT-Dev-GPTQ-Int8

Text Generation
Transformers
Safetensors
multilingual
qwen3
GPTQ
Int8
vLLM
conversational
text-generation-inference
8-bit precision
gptq
Model card Files
xet
Community
JunHowie commited on
Commit
412c277
·
verified ·
1 Parent(s): 51d990d

Add files using upload-large-folder tool

Browse files
Files changed (22) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +117 -0
  4. config.json +120 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00009.safetensors +3 -0
  8. model-00002-of-00009.safetensors +3 -0
  9. model-00003-of-00009.safetensors +3 -0
  10. model-00004-of-00009.safetensors +3 -0
  11. model-00005-of-00009.safetensors +3 -0
  12. model-00006-of-00009.safetensors +3 -0
  13. model-00007-of-00009.safetensors +3 -0
  14. model-00008-of-00009.safetensors +3 -0
  15. model-00009-of-00009.safetensors +3 -0
  16. model.safetensors.index.json +0 -0
  17. quant_log.csv +449 -0
  18. quantize_config.json +24 -0
  19. special_tokens_map.json +25 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +241 -0
  22. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% macro render_extra_keys(json_dict, handled_keys) %}
2
+ {%- if json_dict is mapping %}
3
+ {%- for json_key in json_dict if json_key not in handled_keys %}
4
+ {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
5
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
6
+ {%- else %}
7
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
8
+ {%- endif %}
9
+ {%- endfor %}
10
+ {%- endif %}
11
+ {% endmacro %}
12
+
13
+ {%- if messages[0]["role"] == "system" %}
14
+ {%- set system_message = messages[0]["content"] %}
15
+ {%- set loop_messages = messages[1:] %}
16
+ {%- else %}
17
+ {%- set loop_messages = messages %}
18
+ {%- endif %}
19
+
20
+ {%- if not tools is defined %}
21
+ {%- set tools = [] %}
22
+ {%- endif %}
23
+
24
+ {%- if system_message is defined %}
25
+ {{- "<|im_start|>system\n" + system_message }}
26
+ {%- else %}
27
+ {%- if tools is iterable and tools | length > 0 %}
28
+ {{- "<|im_start|>system\nYou are a helpful AI assistant that can interact with a computer to solve tasks." }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- if tools is iterable and tools | length > 0 %}
32
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
33
+ {{- "<tools>" }}
34
+ {%- for tool in tools %}
35
+ {%- if tool.function is defined %}
36
+ {%- set tool = tool.function %}
37
+ {%- endif %}
38
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
39
+ {%- if tool.description is defined %}
40
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
41
+ {%- endif %}
42
+ {{- '\n<parameters>' }}
43
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
44
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
45
+ {{- '\n<parameter>' }}
46
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
47
+ {%- if param_fields.type is defined %}
48
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
49
+ {%- endif %}
50
+ {%- if param_fields.description is defined %}
51
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
52
+ {%- endif %}
53
+ {%- set handled_keys = ['name', 'type', 'description'] %}
54
+ {{- render_extra_keys(param_fields, handled_keys) }}
55
+ {{- '\n</parameter>' }}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {% set handled_keys = ['type', 'properties'] %}
59
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
60
+ {{- '\n</parameters>' }}
61
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
62
+ {{- render_extra_keys(tool, handled_keys) }}
63
+ {{- '\n</function>' }}
64
+ {%- endfor %}
65
+ {{- "\n</tools>" }}
66
+ {{- '\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>' }}
67
+ {%- endif %}
68
+ {%- if system_message is defined %}
69
+ {{- '<|im_end|>\n' }}
70
+ {%- else %}
71
+ {%- if tools is iterable and tools | length > 0 %}
72
+ {{- '<|im_end|>\n' }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {%- for message in loop_messages %}
76
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
77
+ {{- '<|im_start|>' + message.role }}
78
+ {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
79
+ {{- '\n' + message.content | trim + '\n' }}
80
+ {%- endif %}
81
+ {%- for tool_call in message.tool_calls %}
82
+ {%- if tool_call.function is defined %}
83
+ {%- set tool_call = tool_call.function %}
84
+ {%- endif %}
85
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
86
+ {%- if tool_call.arguments is defined %}
87
+ {%- for args_name, args_value in tool_call.arguments|items %}
88
+ {{- '<parameter=' + args_name + '>\n' }}
89
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
90
+ {{- args_value }}
91
+ {{- '\n</parameter>\n' }}
92
+ {%- endfor %}
93
+ {%- endif %}
94
+ {{- '</function>\n</tool_call>' }}
95
+ {%- endfor %}
96
+ {{- '<|im_end|>\n' }}
97
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
98
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
99
+ {%- elif message.role == "tool" %}
100
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
101
+ {{- '<|im_start|>user\n' }}
102
+ {%- endif %}
103
+ {{- '<tool_response>\n' }}
104
+ {{- message.content }}
105
+ {{- '\n</tool_response>\n' }}
106
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
107
+ {{- '<|im_end|>\n' }}
108
+ {%- elif loop.last %}
109
+ {{- '<|im_end|>\n' }}
110
+ {%- endif %}
111
+ {%- else %}
112
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
113
+ {%- endif %}
114
+ {%- endfor %}
115
+ {%- if add_generation_prompt %}
116
+ {{- '<|im_start|>assistant\n' }}
117
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 25600,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention"
79
+ ],
80
+ "max_position_embeddings": 131072,
81
+ "max_window_layers": 64,
82
+ "model_type": "qwen3",
83
+ "num_attention_heads": 64,
84
+ "num_hidden_layers": 64,
85
+ "num_key_value_heads": 8,
86
+ "pad_token_id": 151643,
87
+ "quantization_config": {
88
+ "bits": 8,
89
+ "checkpoint_format": "gptq",
90
+ "desc_act": false,
91
+ "group_size": 128,
92
+ "lm_head": false,
93
+ "meta": {
94
+ "act_group_aware": false,
95
+ "damp_auto_increment": 0.01,
96
+ "damp_percent": 0.05,
97
+ "mse": 0.0,
98
+ "quantizer": [
99
+ "gptqmodel:4.2.5"
100
+ ],
101
+ "static_groups": false,
102
+ "true_sequential": true,
103
+ "uri": "https://github.com/modelcloud/gptqmodel",
104
+ "v2": false,
105
+ "v2_alpha": 0.25
106
+ },
107
+ "pack_dtype": "int32",
108
+ "quant_method": "gptq",
109
+ "sym": true
110
+ },
111
+ "rms_norm_eps": 1e-06,
112
+ "rope_scaling": null,
113
+ "rope_theta": 1000000,
114
+ "sliding_window": null,
115
+ "tie_word_embeddings": false,
116
+ "transformers_version": "4.56.2",
117
+ "use_cache": false,
118
+ "use_sliding_window": false,
119
+ "vocab_size": 151936
120
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.56.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c14dd6a4b0edfcc1cf467e33bc12991aaf9b8884e23d4d2b3d72a34df6fdb8
3
+ size 3917946328
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c402e24ce05ebb8c61f8b9576516dd33f81cf1f4f30677a8210fb0f06c0258f7
3
+ size 3994222744
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb2af9c3812b780d23a81757d13d2c0762662359006e7c10dae4041ede916b8
3
+ size 3994222936
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf5a5ce1469d98b6ff2528419f9fff2046c3053e1d1402e17c33a28c5e54b66
3
+ size 3994222936
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f50ba7e471ee4f09f1127e2f9430a77428a8cc582fdf096fdbba788f64211a
3
+ size 3994222936
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d90c5a4f65669575a19b07fda0345fe5d1ce90f8664a2decf55390eec2182e63
3
+ size 3994222936
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a4581b6c8af3132c9571dd42742c075c0bc278461b20b2943a4dd5ae38e9c6
3
+ size 3994222936
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167514b2776467fbc8c7ffc65ca6e3f654e73a7b05a6b22db63295233e77b85b
3
+ size 3994222936
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43e643e836157a95bf99b3681e0d8bb3b52e1b79d38d3f05ce3818d038ec57b
3
+ size 3187936208
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quant_log.csv ADDED
@@ -0,0 +1,449 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.0000000001,0.05000,1.288
3
+ 0,self_attn.v_proj,0.0000000000,0.05000,1.053
4
+ 0,self_attn.q_proj,0.0000000003,0.05000,1.088
5
+ 0,self_attn.o_proj,0.0000000014,0.05000,1.801
6
+ 0,mlp.gate_proj,0.0000000090,0.05000,1.144
7
+ 0,mlp.up_proj,0.0000000074,0.05000,1.133
8
+ 0,mlp.down_proj,0.0000000082,0.05000,8.089
9
+ 1,self_attn.k_proj,0.0000000001,0.05000,1.073
10
+ 1,self_attn.v_proj,0.0000000001,0.05000,1.084
11
+ 1,self_attn.q_proj,0.0000000005,0.05000,1.123
12
+ 1,self_attn.o_proj,0.0000000008,0.05000,1.855
13
+ 1,mlp.gate_proj,0.0000005945,0.05000,1.435
14
+ 1,mlp.up_proj,0.0000001761,0.05000,1.165
15
+ 1,mlp.down_proj,0.0000000279,0.05000,8.165
16
+ 2,self_attn.k_proj,0.0000000002,0.05000,1.052
17
+ 2,self_attn.v_proj,0.0000000002,0.05000,1.046
18
+ 2,self_attn.q_proj,0.0000000008,0.05000,1.086
19
+ 2,self_attn.o_proj,0.0000000016,0.05000,1.787
20
+ 2,mlp.gate_proj,0.0000008469,0.05000,1.145
21
+ 2,mlp.up_proj,0.0000003394,0.05000,1.128
22
+ 2,mlp.down_proj,0.0000000263,0.05000,8.158
23
+ 3,self_attn.k_proj,0.0000000003,0.05000,1.070
24
+ 3,self_attn.v_proj,0.0000000003,0.05000,1.049
25
+ 3,self_attn.q_proj,0.0000000015,0.05000,1.089
26
+ 3,self_attn.o_proj,0.0000000016,0.05000,1.795
27
+ 3,mlp.gate_proj,0.0000012168,0.05000,1.168
28
+ 3,mlp.up_proj,0.0000005215,0.05000,1.139
29
+ 3,mlp.down_proj,0.0000000505,0.05000,8.101
30
+ 4,self_attn.k_proj,0.0000000004,0.05000,1.052
31
+ 4,self_attn.v_proj,0.0000000005,0.05000,1.053
32
+ 4,self_attn.q_proj,0.0000000025,0.05000,1.091
33
+ 4,self_attn.o_proj,0.0000000024,0.05000,1.798
34
+ 4,mlp.gate_proj,0.0000015904,0.05000,1.136
35
+ 4,mlp.up_proj,0.0000008837,0.05000,1.127
36
+ 4,mlp.down_proj,0.0000000557,0.05000,8.367
37
+ 5,self_attn.k_proj,0.0000000005,0.05000,1.099
38
+ 5,self_attn.v_proj,0.0000000005,0.05000,1.061
39
+ 5,self_attn.q_proj,0.0000000030,0.05000,1.092
40
+ 5,self_attn.o_proj,0.0000000023,0.05000,1.848
41
+ 5,mlp.gate_proj,0.0000019053,0.05000,1.147
42
+ 5,mlp.up_proj,0.0000008292,0.05000,1.132
43
+ 5,mlp.down_proj,0.0000000781,0.05000,8.128
44
+ 6,self_attn.k_proj,0.0000000007,0.05000,1.072
45
+ 6,self_attn.v_proj,0.0000000007,0.05000,1.055
46
+ 6,self_attn.q_proj,0.0000000038,0.05000,1.083
47
+ 6,self_attn.o_proj,0.0000000026,0.05000,1.811
48
+ 6,mlp.gate_proj,0.0000031318,0.05000,1.155
49
+ 6,mlp.up_proj,0.0000018174,0.05000,1.158
50
+ 6,mlp.down_proj,0.0000243964,0.05000,8.068
51
+ 7,self_attn.k_proj,0.0000000041,0.05000,1.060
52
+ 7,self_attn.v_proj,0.0000000042,0.05000,1.061
53
+ 7,self_attn.q_proj,0.0000000240,0.05000,1.075
54
+ 7,self_attn.o_proj,0.0000000087,0.05000,1.790
55
+ 7,mlp.gate_proj,0.0000034499,0.05000,1.139
56
+ 7,mlp.up_proj,0.0000019170,0.05000,1.124
57
+ 7,mlp.down_proj,0.0000001050,0.05000,8.000
58
+ 8,self_attn.k_proj,0.0000000038,0.05000,1.070
59
+ 8,self_attn.v_proj,0.0000000041,0.05000,1.065
60
+ 8,self_attn.q_proj,0.0000000214,0.05000,1.090
61
+ 8,self_attn.o_proj,0.0000000089,0.05000,1.820
62
+ 8,mlp.gate_proj,0.0000008976,0.05000,1.173
63
+ 8,mlp.up_proj,0.0000004695,0.05000,1.145
64
+ 8,mlp.down_proj,0.0000000659,0.05000,8.079
65
+ 9,self_attn.k_proj,0.0000000021,0.05000,1.084
66
+ 9,self_attn.v_proj,0.0000000022,0.05000,1.074
67
+ 9,self_attn.q_proj,0.0000000116,0.05000,1.093
68
+ 9,self_attn.o_proj,0.0000000056,0.05000,1.818
69
+ 9,mlp.gate_proj,0.0000003811,0.05000,1.142
70
+ 9,mlp.up_proj,0.0000003539,0.05000,1.135
71
+ 9,mlp.down_proj,0.0000000760,0.05000,8.198
72
+ 10,self_attn.k_proj,0.0000000034,0.05000,1.053
73
+ 10,self_attn.v_proj,0.0000000038,0.05000,1.054
74
+ 10,self_attn.q_proj,0.0000000200,0.05000,1.080
75
+ 10,self_attn.o_proj,0.0000000107,0.05000,1.774
76
+ 10,mlp.gate_proj,0.0000003843,0.05000,1.141
77
+ 10,mlp.up_proj,0.0000003651,0.05000,1.144
78
+ 10,mlp.down_proj,0.0000000641,0.05000,8.012
79
+ 11,self_attn.k_proj,0.0000000047,0.05000,1.054
80
+ 11,self_attn.v_proj,0.0000000049,0.05000,1.072
81
+ 11,self_attn.q_proj,0.0000000264,0.05000,1.081
82
+ 11,self_attn.o_proj,0.0000000160,0.05000,1.781
83
+ 11,mlp.gate_proj,0.0000004357,0.05000,1.151
84
+ 11,mlp.up_proj,0.0000004132,0.05000,1.129
85
+ 11,mlp.down_proj,0.0000000755,0.05000,8.050
86
+ 12,self_attn.k_proj,0.0000000032,0.05000,1.073
87
+ 12,self_attn.v_proj,0.0000000035,0.05000,1.062
88
+ 12,self_attn.q_proj,0.0000000187,0.05000,1.090
89
+ 12,self_attn.o_proj,0.0000000083,0.05000,1.791
90
+ 12,mlp.gate_proj,0.0000004875,0.05000,1.458
91
+ 12,mlp.up_proj,0.0000004569,0.05000,1.157
92
+ 12,mlp.down_proj,0.0000000847,0.05000,8.083
93
+ 13,self_attn.k_proj,0.0000000061,0.05000,1.079
94
+ 13,self_attn.v_proj,0.0000000066,0.05000,1.063
95
+ 13,self_attn.q_proj,0.0000000353,0.05000,1.086
96
+ 13,self_attn.o_proj,0.0000000130,0.05000,1.788
97
+ 13,mlp.gate_proj,0.0000005081,0.05000,1.136
98
+ 13,mlp.up_proj,0.0000004603,0.05000,1.134
99
+ 13,mlp.down_proj,0.0000000843,0.05000,8.092
100
+ 14,self_attn.k_proj,0.0000000032,0.05000,1.061
101
+ 14,self_attn.v_proj,0.0000000034,0.05000,1.075
102
+ 14,self_attn.q_proj,0.0000000166,0.05000,1.115
103
+ 14,self_attn.o_proj,0.0000000120,0.05000,1.804
104
+ 14,mlp.gate_proj,0.0000004667,0.05000,1.197
105
+ 14,mlp.up_proj,0.0000004306,0.05000,1.134
106
+ 14,mlp.down_proj,0.0000000771,0.05000,8.094
107
+ 15,self_attn.k_proj,0.0000000030,0.05000,1.053
108
+ 15,self_attn.v_proj,0.0000000032,0.05000,1.053
109
+ 15,self_attn.q_proj,0.0000000177,0.05000,1.083
110
+ 15,self_attn.o_proj,0.0000000121,0.05000,1.799
111
+ 15,mlp.gate_proj,0.0000004142,0.05000,1.163
112
+ 15,mlp.up_proj,0.0000003936,0.05000,1.131
113
+ 15,mlp.down_proj,0.0000000687,0.05000,8.023
114
+ 16,self_attn.k_proj,0.0000000029,0.05000,1.057
115
+ 16,self_attn.v_proj,0.0000000032,0.05000,1.058
116
+ 16,self_attn.q_proj,0.0000000168,0.05000,1.081
117
+ 16,self_attn.o_proj,0.0000000119,0.05000,1.794
118
+ 16,mlp.gate_proj,0.0000003634,0.05000,1.129
119
+ 16,mlp.up_proj,0.0000003448,0.05000,1.121
120
+ 16,mlp.down_proj,0.0000000619,0.05000,8.011
121
+ 17,self_attn.k_proj,0.0000000030,0.05000,1.059
122
+ 17,self_attn.v_proj,0.0000000030,0.05000,1.051
123
+ 17,self_attn.q_proj,0.0000000170,0.05000,1.091
124
+ 17,self_attn.o_proj,0.0000000118,0.05000,1.783
125
+ 17,mlp.gate_proj,0.0000003754,0.05000,1.191
126
+ 17,mlp.up_proj,0.0000003556,0.05000,1.147
127
+ 17,mlp.down_proj,0.0000000640,0.05000,8.066
128
+ 18,self_attn.k_proj,0.0000000039,0.05000,1.065
129
+ 18,self_attn.v_proj,0.0000000040,0.05000,1.046
130
+ 18,self_attn.q_proj,0.0000000226,0.05000,1.081
131
+ 18,self_attn.o_proj,0.0000000114,0.05000,1.777
132
+ 18,mlp.gate_proj,0.0000003997,0.05000,1.128
133
+ 18,mlp.up_proj,0.0000003759,0.05000,1.122
134
+ 18,mlp.down_proj,0.0000000713,0.05000,8.026
135
+ 19,self_attn.k_proj,0.0000000044,0.05000,1.074
136
+ 19,self_attn.v_proj,0.0000000045,0.05000,1.050
137
+ 19,self_attn.q_proj,0.0000000264,0.05000,1.075
138
+ 19,self_attn.o_proj,0.0000000157,0.05000,1.778
139
+ 19,mlp.gate_proj,0.0000004350,0.05000,1.172
140
+ 19,mlp.up_proj,0.0000004132,0.05000,1.132
141
+ 19,mlp.down_proj,0.0000000835,0.05000,8.047
142
+ 20,self_attn.k_proj,0.0000000074,0.05000,1.055
143
+ 20,self_attn.v_proj,0.0000000080,0.05000,1.055
144
+ 20,self_attn.q_proj,0.0000000429,0.05000,1.091
145
+ 20,self_attn.o_proj,0.0000000161,0.05000,2.024
146
+ 20,mlp.gate_proj,0.0000004741,0.05000,1.158
147
+ 20,mlp.up_proj,0.0000004521,0.05000,1.155
148
+ 20,mlp.down_proj,0.0000000936,0.05000,8.202
149
+ 21,self_attn.k_proj,0.0000000083,0.05000,1.073
150
+ 21,self_attn.v_proj,0.0000000087,0.05000,1.119
151
+ 21,self_attn.q_proj,0.0000000484,0.05000,1.131
152
+ 21,self_attn.o_proj,0.0000000298,0.05000,1.824
153
+ 21,mlp.gate_proj,0.0000004994,0.05000,1.154
154
+ 21,mlp.up_proj,0.0000004764,0.05000,1.157
155
+ 21,mlp.down_proj,0.0000001065,0.05000,8.209
156
+ 22,self_attn.k_proj,0.0000000072,0.05000,1.063
157
+ 22,self_attn.v_proj,0.0000000079,0.05000,1.095
158
+ 22,self_attn.q_proj,0.0000000437,0.05000,1.077
159
+ 22,self_attn.o_proj,0.0000000361,0.05000,1.771
160
+ 22,mlp.gate_proj,0.0000005477,0.05000,1.312
161
+ 22,mlp.up_proj,0.0000005222,0.05000,1.132
162
+ 22,mlp.down_proj,0.0000001284,0.05000,8.103
163
+ 23,self_attn.k_proj,0.0000000101,0.05000,1.071
164
+ 23,self_attn.v_proj,0.0000000115,0.05000,1.052
165
+ 23,self_attn.q_proj,0.0000000579,0.05000,1.072
166
+ 23,self_attn.o_proj,0.0000000244,0.05000,1.775
167
+ 23,mlp.gate_proj,0.0000006019,0.05000,1.155
168
+ 23,mlp.up_proj,0.0000005727,0.05000,1.127
169
+ 23,mlp.down_proj,0.0000001546,0.05000,8.118
170
+ 24,self_attn.k_proj,0.0000000180,0.05000,1.061
171
+ 24,self_attn.v_proj,0.0000000202,0.05000,1.060
172
+ 24,self_attn.q_proj,0.0000001111,0.05000,1.088
173
+ 24,self_attn.o_proj,0.0000000532,0.05000,1.775
174
+ 24,mlp.gate_proj,0.0000006775,0.05000,1.128
175
+ 24,mlp.up_proj,0.0000006410,0.05000,1.127
176
+ 24,mlp.down_proj,0.0000001807,0.05000,8.006
177
+ 25,self_attn.k_proj,0.0000000156,0.05000,1.049
178
+ 25,self_attn.v_proj,0.0000000172,0.05000,1.058
179
+ 25,self_attn.q_proj,0.0000000929,0.05000,1.085
180
+ 25,self_attn.o_proj,0.0000000478,0.05000,1.796
181
+ 25,mlp.gate_proj,0.0000007617,0.05000,1.158
182
+ 25,mlp.up_proj,0.0000007163,0.05000,1.131
183
+ 25,mlp.down_proj,0.0000002311,0.05000,8.343
184
+ 26,self_attn.k_proj,0.0000000142,0.05000,1.068
185
+ 26,self_attn.v_proj,0.0000000165,0.05000,1.068
186
+ 26,self_attn.q_proj,0.0000000837,0.05000,1.081
187
+ 26,self_attn.o_proj,0.0000000437,0.05000,1.788
188
+ 26,mlp.gate_proj,0.0000008507,0.05000,1.128
189
+ 26,mlp.up_proj,0.0000007863,0.05000,1.129
190
+ 26,mlp.down_proj,0.0000002909,0.05000,8.068
191
+ 27,self_attn.k_proj,0.0000000211,0.05000,1.059
192
+ 27,self_attn.v_proj,0.0000000250,0.05000,1.060
193
+ 27,self_attn.q_proj,0.0000001197,0.05000,1.084
194
+ 27,self_attn.o_proj,0.0000000480,0.05000,1.805
195
+ 27,mlp.gate_proj,0.0000009910,0.05000,1.141
196
+ 27,mlp.up_proj,0.0000008987,0.05000,1.136
197
+ 27,mlp.down_proj,0.0000003665,0.05000,8.014
198
+ 28,self_attn.k_proj,0.0000000269,0.05000,1.047
199
+ 28,self_attn.v_proj,0.0000000321,0.05000,1.052
200
+ 28,self_attn.q_proj,0.0000001592,0.05000,1.249
201
+ 28,self_attn.o_proj,0.0000000531,0.05000,1.784
202
+ 28,mlp.gate_proj,0.0000011194,0.05000,1.135
203
+ 28,mlp.up_proj,0.0000010198,0.05000,1.148
204
+ 28,mlp.down_proj,0.0000004061,0.05000,8.040
205
+ 29,self_attn.k_proj,0.0000000400,0.05000,1.061
206
+ 29,self_attn.v_proj,0.0000000427,0.05000,1.059
207
+ 29,self_attn.q_proj,0.0000002190,0.05000,1.081
208
+ 29,self_attn.o_proj,0.0000000459,0.05000,1.799
209
+ 29,mlp.gate_proj,0.0000012452,0.05000,1.166
210
+ 29,mlp.up_proj,0.0000010774,0.05000,1.134
211
+ 29,mlp.down_proj,0.0000004184,0.05000,8.122
212
+ 30,self_attn.k_proj,0.0000000822,0.05000,1.069
213
+ 30,self_attn.v_proj,0.0000001094,0.05000,1.054
214
+ 30,self_attn.q_proj,0.0000004353,0.05000,1.083
215
+ 30,self_attn.o_proj,0.0000000581,0.05000,1.783
216
+ 30,mlp.gate_proj,0.0000020782,0.05000,1.159
217
+ 30,mlp.up_proj,0.0000013648,0.05000,1.141
218
+ 30,mlp.down_proj,0.0000003798,0.05000,8.176
219
+ 31,self_attn.k_proj,0.0000000687,0.05000,1.058
220
+ 31,self_attn.v_proj,0.0000000767,0.05000,1.055
221
+ 31,self_attn.q_proj,0.0000003481,0.05000,1.088
222
+ 31,self_attn.o_proj,0.0000000595,0.05000,1.818
223
+ 31,mlp.gate_proj,0.0000035998,0.05000,1.136
224
+ 31,mlp.up_proj,0.0000025057,0.05000,1.147
225
+ 31,mlp.down_proj,0.0000003782,0.05000,8.108
226
+ 32,self_attn.k_proj,0.0000000198,0.05000,1.061
227
+ 32,self_attn.v_proj,0.0000000252,0.05000,1.060
228
+ 32,self_attn.q_proj,0.0000001136,0.05000,1.090
229
+ 32,self_attn.o_proj,0.0000000463,0.05000,1.815
230
+ 32,mlp.gate_proj,0.0000018849,0.05000,1.139
231
+ 32,mlp.up_proj,0.0000013548,0.05000,1.146
232
+ 32,mlp.down_proj,0.0000003645,0.05000,8.137
233
+ 33,self_attn.k_proj,0.0000000168,0.05000,1.083
234
+ 33,self_attn.v_proj,0.0000000173,0.05000,1.083
235
+ 33,self_attn.q_proj,0.0000000920,0.05000,1.117
236
+ 33,self_attn.o_proj,0.0000000350,0.05000,1.823
237
+ 33,mlp.gate_proj,0.0000012446,0.05000,1.182
238
+ 33,mlp.up_proj,0.0000011373,0.05000,1.167
239
+ 33,mlp.down_proj,0.0000003680,0.05000,8.073
240
+ 34,self_attn.k_proj,0.0000000227,0.05000,1.079
241
+ 34,self_attn.v_proj,0.0000000258,0.05000,1.066
242
+ 34,self_attn.q_proj,0.0000001392,0.05000,1.339
243
+ 34,self_attn.o_proj,0.0000000530,0.05000,1.833
244
+ 34,mlp.gate_proj,0.0000011180,0.05000,1.150
245
+ 34,mlp.up_proj,0.0000010661,0.05000,1.144
246
+ 34,mlp.down_proj,0.0000002927,0.05000,8.110
247
+ 35,self_attn.k_proj,0.0000000270,0.05000,1.073
248
+ 35,self_attn.v_proj,0.0000000309,0.05000,1.071
249
+ 35,self_attn.q_proj,0.0000001656,0.05000,1.108
250
+ 35,self_attn.o_proj,0.0000000654,0.05000,1.803
251
+ 35,mlp.gate_proj,0.0000012108,0.05000,1.183
252
+ 35,mlp.up_proj,0.0000011538,0.05000,1.154
253
+ 35,mlp.down_proj,0.0000003264,0.05000,8.186
254
+ 36,self_attn.k_proj,0.0000000170,0.05000,1.107
255
+ 36,self_attn.v_proj,0.0000000196,0.05000,1.085
256
+ 36,self_attn.q_proj,0.0000001047,0.05000,1.127
257
+ 36,self_attn.o_proj,0.0000000497,0.05000,1.968
258
+ 36,mlp.gate_proj,0.0000012861,0.05000,1.163
259
+ 36,mlp.up_proj,0.0000012257,0.05000,1.146
260
+ 36,mlp.down_proj,0.0000003653,0.05000,8.104
261
+ 37,self_attn.k_proj,0.0000000348,0.05000,1.096
262
+ 37,self_attn.v_proj,0.0000000401,0.05000,1.058
263
+ 37,self_attn.q_proj,0.0000002120,0.05000,1.085
264
+ 37,self_attn.o_proj,0.0000000902,0.05000,1.806
265
+ 37,mlp.gate_proj,0.0000013586,0.05000,1.141
266
+ 37,mlp.up_proj,0.0000012513,0.05000,1.139
267
+ 37,mlp.down_proj,0.0000003713,0.05000,8.122
268
+ 38,self_attn.k_proj,0.0000000232,0.05000,1.067
269
+ 38,self_attn.v_proj,0.0000000266,0.05000,1.054
270
+ 38,self_attn.q_proj,0.0000001376,0.05000,1.368
271
+ 38,self_attn.o_proj,0.0000000780,0.05000,1.994
272
+ 38,mlp.gate_proj,0.0000011868,0.05000,1.142
273
+ 38,mlp.up_proj,0.0000011394,0.05000,1.129
274
+ 38,mlp.down_proj,0.0000003501,0.05000,8.108
275
+ 39,self_attn.k_proj,0.0000000213,0.05000,1.048
276
+ 39,self_attn.v_proj,0.0000000227,0.05000,1.054
277
+ 39,self_attn.q_proj,0.0000001309,0.05000,1.081
278
+ 39,self_attn.o_proj,0.0000000804,0.05000,1.784
279
+ 39,mlp.gate_proj,0.0000010609,0.05000,1.133
280
+ 39,mlp.up_proj,0.0000010860,0.05000,1.147
281
+ 39,mlp.down_proj,0.0000003394,0.05000,8.063
282
+ 40,self_attn.k_proj,0.0000000258,0.05000,1.055
283
+ 40,self_attn.v_proj,0.0000000295,0.05000,1.056
284
+ 40,self_attn.q_proj,0.0000001592,0.05000,1.088
285
+ 40,self_attn.o_proj,0.0000001073,0.05000,1.806
286
+ 40,mlp.gate_proj,0.0000009110,0.05000,1.163
287
+ 40,mlp.up_proj,0.0000009841,0.05000,1.139
288
+ 40,mlp.down_proj,0.0000003317,0.05000,8.082
289
+ 41,self_attn.k_proj,0.0000000254,0.05000,1.062
290
+ 41,self_attn.v_proj,0.0000000279,0.05000,1.070
291
+ 41,self_attn.q_proj,0.0000001642,0.05000,1.136
292
+ 41,self_attn.o_proj,0.0000001032,0.05000,1.798
293
+ 41,mlp.gate_proj,0.0000009360,0.05000,1.158
294
+ 41,mlp.up_proj,0.0000010260,0.05000,1.135
295
+ 41,mlp.down_proj,0.0000003328,0.05000,8.076
296
+ 42,self_attn.k_proj,0.0000000344,0.05000,1.057
297
+ 42,self_attn.v_proj,0.0000000398,0.05000,1.059
298
+ 42,self_attn.q_proj,0.0000002262,0.05000,1.087
299
+ 42,self_attn.o_proj,0.0000001137,0.05000,1.780
300
+ 42,mlp.gate_proj,0.0000009660,0.05000,1.144
301
+ 42,mlp.up_proj,0.0000010853,0.05000,1.130
302
+ 42,mlp.down_proj,0.0000003526,0.05000,8.144
303
+ 43,self_attn.k_proj,0.0000000497,0.05000,1.067
304
+ 43,self_attn.v_proj,0.0000000559,0.05000,1.063
305
+ 43,self_attn.q_proj,0.0000003056,0.05000,1.101
306
+ 43,self_attn.o_proj,0.0000001351,0.05000,2.057
307
+ 43,mlp.gate_proj,0.0000010626,0.05000,1.137
308
+ 43,mlp.up_proj,0.0000011683,0.05000,1.138
309
+ 43,mlp.down_proj,0.0000011667,0.05000,8.109
310
+ 44,self_attn.k_proj,0.0000000747,0.05000,1.065
311
+ 44,self_attn.v_proj,0.0000000937,0.05000,1.070
312
+ 44,self_attn.q_proj,0.0000005108,0.05000,1.206
313
+ 44,self_attn.o_proj,0.0000001612,0.05000,1.801
314
+ 44,mlp.gate_proj,0.0000010736,0.05000,1.145
315
+ 44,mlp.up_proj,0.0000011866,0.05000,1.166
316
+ 44,mlp.down_proj,0.0000004237,0.05000,8.079
317
+ 45,self_attn.k_proj,0.0000000790,0.05000,1.053
318
+ 45,self_attn.v_proj,0.0000000818,0.05000,1.091
319
+ 45,self_attn.q_proj,0.0000004566,0.05000,1.117
320
+ 45,self_attn.o_proj,0.0000002097,0.05000,1.864
321
+ 45,mlp.gate_proj,0.0000010832,0.05000,1.182
322
+ 45,mlp.up_proj,0.0000011737,0.05000,1.157
323
+ 45,mlp.down_proj,0.0000004474,0.05000,8.165
324
+ 46,self_attn.k_proj,0.0000000693,0.05000,1.068
325
+ 46,self_attn.v_proj,0.0000000873,0.05000,1.060
326
+ 46,self_attn.q_proj,0.0000004537,0.05000,1.107
327
+ 46,self_attn.o_proj,0.0000002005,0.05000,1.827
328
+ 46,mlp.gate_proj,0.0000011403,0.05000,1.475
329
+ 46,mlp.up_proj,0.0000012355,0.05000,1.181
330
+ 46,mlp.down_proj,0.0000004723,0.05000,8.160
331
+ 47,self_attn.k_proj,0.0000000973,0.05000,1.089
332
+ 47,self_attn.v_proj,0.0000001358,0.05000,1.088
333
+ 47,self_attn.q_proj,0.0000006704,0.05000,1.097
334
+ 47,self_attn.o_proj,0.0000001611,0.05000,1.844
335
+ 47,mlp.gate_proj,0.0000011614,0.05000,1.446
336
+ 47,mlp.up_proj,0.0000012489,0.05000,1.232
337
+ 47,mlp.down_proj,0.0000005587,0.05000,8.508
338
+ 48,self_attn.k_proj,0.0000001117,0.05000,1.152
339
+ 48,self_attn.v_proj,0.0000001522,0.05000,1.167
340
+ 48,self_attn.q_proj,0.0000007989,0.05000,1.222
341
+ 48,self_attn.o_proj,0.0000002700,0.05000,1.998
342
+ 48,mlp.gate_proj,0.0000012734,0.05000,1.235
343
+ 48,mlp.up_proj,0.0000013358,0.05000,1.236
344
+ 48,mlp.down_proj,0.0000005997,0.05000,8.494
345
+ 49,self_attn.k_proj,0.0000001183,0.05000,1.080
346
+ 49,self_attn.v_proj,0.0000001463,0.05000,1.069
347
+ 49,self_attn.q_proj,0.0000007858,0.05000,1.091
348
+ 49,self_attn.o_proj,0.0000002491,0.05000,1.848
349
+ 49,mlp.gate_proj,0.0000014685,0.05000,1.146
350
+ 49,mlp.up_proj,0.0000015074,0.05000,1.138
351
+ 49,mlp.down_proj,0.0000008521,0.05000,8.053
352
+ 50,self_attn.k_proj,0.0000001243,0.05000,1.061
353
+ 50,self_attn.v_proj,0.0000001691,0.05000,1.067
354
+ 50,self_attn.q_proj,0.0000008871,0.05000,1.110
355
+ 50,self_attn.o_proj,0.0000002494,0.05000,1.809
356
+ 50,mlp.gate_proj,0.0000017845,0.05000,1.141
357
+ 50,mlp.up_proj,0.0000017845,0.05000,1.153
358
+ 50,mlp.down_proj,0.0000013748,0.05000,8.080
359
+ 51,self_attn.k_proj,0.0000002210,0.05000,1.077
360
+ 51,self_attn.v_proj,0.0000002929,0.05000,1.073
361
+ 51,self_attn.q_proj,0.0000015005,0.05000,1.088
362
+ 51,self_attn.o_proj,0.0000004835,0.05000,1.842
363
+ 51,mlp.gate_proj,0.0000022806,0.05000,1.143
364
+ 51,mlp.up_proj,0.0000022662,0.05000,1.133
365
+ 51,mlp.down_proj,0.0000021119,0.05000,8.091
366
+ 52,self_attn.k_proj,0.0000002995,0.05000,1.066
367
+ 52,self_attn.v_proj,0.0000004575,0.05000,1.079
368
+ 52,self_attn.q_proj,0.0000023181,0.05000,1.087
369
+ 52,self_attn.o_proj,0.0000005232,0.05000,1.791
370
+ 52,mlp.gate_proj,0.0000028979,0.05000,1.169
371
+ 52,mlp.up_proj,0.0000029187,0.05000,1.141
372
+ 52,mlp.down_proj,0.0000028068,0.05000,8.117
373
+ 53,self_attn.k_proj,0.0000004835,0.05000,1.067
374
+ 53,self_attn.v_proj,0.0000006293,0.05000,1.066
375
+ 53,self_attn.q_proj,0.0000033281,0.05000,1.095
376
+ 53,self_attn.o_proj,0.0000004941,0.05000,1.805
377
+ 53,mlp.gate_proj,0.0000033495,0.05000,1.158
378
+ 53,mlp.up_proj,0.0000034203,0.05000,1.147
379
+ 53,mlp.down_proj,0.0000042661,0.05000,8.111
380
+ 54,self_attn.k_proj,0.0000007604,0.05000,1.082
381
+ 54,self_attn.v_proj,0.0000011072,0.05000,1.071
382
+ 54,self_attn.q_proj,0.0000052773,0.05000,1.094
383
+ 54,self_attn.o_proj,0.0000010223,0.05000,1.880
384
+ 54,mlp.gate_proj,0.0000045094,0.05000,1.157
385
+ 54,mlp.up_proj,0.0000045872,0.05000,1.152
386
+ 54,mlp.down_proj,0.0000055971,0.05000,8.075
387
+ 55,self_attn.k_proj,0.0000008375,0.05000,1.059
388
+ 55,self_attn.v_proj,0.0000010303,0.05000,1.076
389
+ 55,self_attn.q_proj,0.0000056554,0.05000,1.103
390
+ 55,self_attn.o_proj,0.0000009534,0.05000,1.793
391
+ 55,mlp.gate_proj,0.0000050994,0.05000,1.144
392
+ 55,mlp.up_proj,0.0000052824,0.05000,1.142
393
+ 55,mlp.down_proj,0.0000075244,0.05000,8.080
394
+ 56,self_attn.k_proj,0.0000014614,0.05000,1.091
395
+ 56,self_attn.v_proj,0.0000022171,0.05000,1.072
396
+ 56,self_attn.q_proj,0.0000102127,0.05000,1.181
397
+ 56,self_attn.o_proj,0.0000010268,0.05000,1.821
398
+ 56,mlp.gate_proj,0.0000059043,0.05000,1.177
399
+ 56,mlp.up_proj,0.0000062138,0.05000,1.150
400
+ 56,mlp.down_proj,0.0000095164,0.05000,8.104
401
+ 57,self_attn.k_proj,0.0000018241,0.05000,1.081
402
+ 57,self_attn.v_proj,0.0000028335,0.05000,1.081
403
+ 57,self_attn.q_proj,0.0000133045,0.05000,1.121
404
+ 57,self_attn.o_proj,0.0000012992,0.05000,1.819
405
+ 57,mlp.gate_proj,0.0000064606,0.05000,1.169
406
+ 57,mlp.up_proj,0.0000069776,0.05000,1.161
407
+ 57,mlp.down_proj,0.0000126919,0.05000,8.196
408
+ 58,self_attn.k_proj,0.0000029728,0.05000,1.091
409
+ 58,self_attn.v_proj,0.0000046122,0.05000,1.089
410
+ 58,self_attn.q_proj,0.0000212859,0.05000,1.110
411
+ 58,self_attn.o_proj,0.0000014744,0.05000,1.833
412
+ 58,mlp.gate_proj,0.0000073618,0.05000,1.163
413
+ 58,mlp.up_proj,0.0000080955,0.05000,1.154
414
+ 58,mlp.down_proj,0.0000166249,0.05000,8.277
415
+ 59,self_attn.k_proj,0.0000036624,0.05000,1.078
416
+ 59,self_attn.v_proj,0.0000059932,0.05000,1.058
417
+ 59,self_attn.q_proj,0.0000267212,0.05000,1.213
418
+ 59,self_attn.o_proj,0.0000014935,0.05000,1.820
419
+ 59,mlp.gate_proj,0.0000081891,0.05000,1.167
420
+ 59,mlp.up_proj,0.0000090891,0.05000,1.152
421
+ 59,mlp.down_proj,0.0000255458,0.05000,9.124
422
+ 60,self_attn.k_proj,0.0000040584,0.05000,1.071
423
+ 60,self_attn.v_proj,0.0000062538,0.05000,1.065
424
+ 60,self_attn.q_proj,0.0000271068,0.05000,1.128
425
+ 60,self_attn.o_proj,0.0000041404,0.05000,1.871
426
+ 60,mlp.gate_proj,0.0000088629,0.05000,1.359
427
+ 60,mlp.up_proj,0.0000101049,0.05000,1.145
428
+ 60,mlp.down_proj,0.0000384820,0.05000,8.277
429
+ 61,self_attn.k_proj,0.0000054317,0.05000,1.064
430
+ 61,self_attn.v_proj,0.0000094258,0.05000,1.071
431
+ 61,self_attn.q_proj,0.0000391906,0.05000,1.465
432
+ 61,self_attn.o_proj,0.0000042686,0.05000,1.841
433
+ 61,mlp.gate_proj,0.0000094184,0.05000,1.224
434
+ 61,mlp.up_proj,0.0000108588,0.05000,1.187
435
+ 61,mlp.down_proj,0.0000550679,0.05000,8.119
436
+ 62,self_attn.k_proj,0.0000056649,0.05000,1.081
437
+ 62,self_attn.v_proj,0.0000101746,0.05000,1.068
438
+ 62,self_attn.q_proj,0.0000392652,0.05000,1.092
439
+ 62,self_attn.o_proj,0.0000079702,0.05000,1.833
440
+ 62,mlp.gate_proj,0.0000116558,0.05000,1.144
441
+ 62,mlp.up_proj,0.0000129260,0.05000,1.141
442
+ 62,mlp.down_proj,0.0000882188,0.05000,8.091
443
+ 63,self_attn.k_proj,0.0000026408,0.05000,1.064
444
+ 63,self_attn.v_proj,0.0000040543,0.05000,1.087
445
+ 63,self_attn.q_proj,0.0000181348,0.05000,1.091
446
+ 63,self_attn.o_proj,0.0000071743,0.05000,1.828
447
+ 63,mlp.gate_proj,0.0000143294,0.05000,1.148
448
+ 63,mlp.up_proj,0.0000155459,0.05000,1.141
449
+ 63,mlp.down_proj,0.0003312480,0.05000,8.298
quantize_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 8,
3
+ "group_size": 128,
4
+ "desc_act": false,
5
+ "sym": true,
6
+ "lm_head": false,
7
+ "quant_method": "gptq",
8
+ "checkpoint_format": "gptq",
9
+ "pack_dtype": "int32",
10
+ "meta": {
11
+ "quantizer": [
12
+ "gptqmodel:4.2.5"
13
+ ],
14
+ "uri": "https://github.com/modelcloud/gptqmodel",
15
+ "damp_percent": 0.05,
16
+ "damp_auto_increment": 0.01,
17
+ "static_groups": false,
18
+ "true_sequential": true,
19
+ "mse": 0.0,
20
+ "v2": false,
21
+ "v2_alpha": 0.25,
22
+ "act_group_aware": false
23
+ }
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2TokenizerFast",
239
+ "unk_token": null,
240
+ "_commit_hash": null
241
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff