Hugging Face's logo

QuantTrio
/
KAT-Dev-GPTQ-Int4

Text Generation
Transformers
Safetensors
multilingual
qwen3
GPTQ
Int4
vLLM
conversational
text-generation-inference
4-bit precision
gptq
Model card Files
xet
Community
JunHowie commited on
Commit
adca516
·
verified ·
1 Parent(s): 937f570

Add files using upload-large-folder tool

Browse files
Files changed (18) 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-00005.safetensors +3 -0
  8. model-00002-of-00005.safetensors +3 -0
  9. model-00003-of-00005.safetensors +3 -0
  10. model-00004-of-00005.safetensors +3 -0
  11. model-00005-of-00005.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
  13. quant_log.csv +449 -0
  14. quantize_config.json +24 -0
  15. special_tokens_map.json +25 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +241 -0
  18. 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": 4,
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-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3ce822b5879263d052dd03fa1eff2f07a60f3ea83b8869936d110e7e5c21f8
3
+ size 3955280848
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a423076e328bbfb7ec6ac84e10a63a868637ab4c8b6d4037e4428b970b572f
3
+ size 3989151776
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f996f378c1b5382a28a914a25fa2889f49aafdd582d6c1a8994811f61ee51d9
3
+ size 3939923288
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7221ada0047e6151d3e31af16af04a58f66a85214c48b9a6fd689f65305e9bb
3
+ size 3989151824
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2391b141b28b8201111096b54bac87a47c45cfded1379deacf8e6073e126b3
3
+ size 3467226552
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,0.0000000162,0.05000,3.234
3
+ 0,self_attn.v_proj,0.0000000127,0.05000,1.044
4
+ 0,self_attn.q_proj,0.0000000816,0.05000,1.081
5
+ 0,self_attn.o_proj,0.0000004007,0.05000,1.772
6
+ 0,mlp.gate_proj,0.0000024797,0.05000,1.139
7
+ 0,mlp.up_proj,0.0000021738,0.05000,1.122
8
+ 0,mlp.down_proj,0.0000023848,0.05000,8.001
9
+ 1,self_attn.k_proj,0.0000000269,0.05000,1.034
10
+ 1,self_attn.v_proj,0.0000000269,0.05000,1.033
11
+ 1,self_attn.q_proj,0.0000001541,0.05000,1.057
12
+ 1,self_attn.o_proj,0.0000002456,0.05000,2.065
13
+ 1,mlp.gate_proj,0.0001649253,0.05000,1.130
14
+ 1,mlp.up_proj,0.0000509813,0.05000,1.139
15
+ 1,mlp.down_proj,0.0000078315,0.05000,8.037
16
+ 2,self_attn.k_proj,0.0000000458,0.05000,1.044
17
+ 2,self_attn.v_proj,0.0000000446,0.05000,1.042
18
+ 2,self_attn.q_proj,0.0000002448,0.05000,1.073
19
+ 2,self_attn.o_proj,0.0000004594,0.05000,1.767
20
+ 2,mlp.gate_proj,0.0002349929,0.05000,1.133
21
+ 2,mlp.up_proj,0.0000981800,0.05000,1.123
22
+ 2,mlp.down_proj,0.0000073423,0.05000,8.280
23
+ 3,self_attn.k_proj,0.0000000833,0.05000,1.046
24
+ 3,self_attn.v_proj,0.0000000865,0.05000,1.036
25
+ 3,self_attn.q_proj,0.0000004506,0.05000,1.061
26
+ 3,self_attn.o_proj,0.0000004512,0.05000,1.760
27
+ 3,mlp.gate_proj,0.0003456217,0.05000,1.165
28
+ 3,mlp.up_proj,0.0001514415,0.05000,1.139
29
+ 3,mlp.down_proj,0.0000142816,0.05000,8.122
30
+ 4,self_attn.k_proj,0.0000001313,0.05000,1.087
31
+ 4,self_attn.v_proj,0.0000001358,0.05000,1.077
32
+ 4,self_attn.q_proj,0.0000007362,0.05000,1.086
33
+ 4,self_attn.o_proj,0.0000006806,0.05000,1.787
34
+ 4,mlp.gate_proj,0.0004579198,0.05000,1.393
35
+ 4,mlp.up_proj,0.0002564290,0.05000,1.235
36
+ 4,mlp.down_proj,0.0000159178,0.05000,8.022
37
+ 5,self_attn.k_proj,0.0000001601,0.05000,1.057
38
+ 5,self_attn.v_proj,0.0000001558,0.05000,1.053
39
+ 5,self_attn.q_proj,0.0000008758,0.05000,1.111
40
+ 5,self_attn.o_proj,0.0000006760,0.05000,1.793
41
+ 5,mlp.gate_proj,0.0005507642,0.05000,1.163
42
+ 5,mlp.up_proj,0.0002391874,0.05000,1.142
43
+ 5,mlp.down_proj,0.0000223429,0.05000,7.979
44
+ 6,self_attn.k_proj,0.0000001918,0.05000,1.062
45
+ 6,self_attn.v_proj,0.0000002022,0.05000,1.049
46
+ 6,self_attn.q_proj,0.0000011141,0.05000,1.076
47
+ 6,self_attn.o_proj,0.0000007390,0.05000,1.766
48
+ 6,mlp.gate_proj,0.0009107982,0.05000,1.126
49
+ 6,mlp.up_proj,0.0005256533,0.05000,1.121
50
+ 6,mlp.down_proj,0.0043096024,0.05000,7.967
51
+ 7,self_attn.k_proj,0.0000011770,0.05000,1.037
52
+ 7,self_attn.v_proj,0.0000012232,0.05000,1.034
53
+ 7,self_attn.q_proj,0.0000069287,0.05000,1.058
54
+ 7,self_attn.o_proj,0.0000025039,0.05000,1.751
55
+ 7,mlp.gate_proj,0.0009953627,0.05000,1.117
56
+ 7,mlp.up_proj,0.0005493904,0.05000,1.125
57
+ 7,mlp.down_proj,0.0000297612,0.05000,7.977
58
+ 8,self_attn.k_proj,0.0000010946,0.05000,1.069
59
+ 8,self_attn.v_proj,0.0000011919,0.05000,1.056
60
+ 8,self_attn.q_proj,0.0000061875,0.05000,1.069
61
+ 8,self_attn.o_proj,0.0000025796,0.05000,1.768
62
+ 8,mlp.gate_proj,0.0002623779,0.05000,1.124
63
+ 8,mlp.up_proj,0.0001344016,0.05000,1.116
64
+ 8,mlp.down_proj,0.0000189611,0.05000,7.998
65
+ 9,self_attn.k_proj,0.0000006171,0.05000,1.059
66
+ 9,self_attn.v_proj,0.0000006324,0.05000,1.072
67
+ 9,self_attn.q_proj,0.0000033820,0.05000,1.084
68
+ 9,self_attn.o_proj,0.0000015995,0.05000,1.779
69
+ 9,mlp.gate_proj,0.0001099972,0.05000,1.142
70
+ 9,mlp.up_proj,0.0001023062,0.05000,1.150
71
+ 9,mlp.down_proj,0.0000218911,0.05000,7.992
72
+ 10,self_attn.k_proj,0.0000009853,0.05000,1.044
73
+ 10,self_attn.v_proj,0.0000011111,0.05000,1.036
74
+ 10,self_attn.q_proj,0.0000058205,0.05000,1.061
75
+ 10,self_attn.o_proj,0.0000031338,0.05000,1.750
76
+ 10,mlp.gate_proj,0.0001112629,0.05000,1.220
77
+ 10,mlp.up_proj,0.0001056672,0.05000,1.115
78
+ 10,mlp.down_proj,0.0000184607,0.05000,8.407
79
+ 11,self_attn.k_proj,0.0000013373,0.05000,1.040
80
+ 11,self_attn.v_proj,0.0000014252,0.05000,1.057
81
+ 11,self_attn.q_proj,0.0000076782,0.05000,1.102
82
+ 11,self_attn.o_proj,0.0000045550,0.05000,1.756
83
+ 11,mlp.gate_proj,0.0001260963,0.05000,1.126
84
+ 11,mlp.up_proj,0.0001195048,0.05000,1.119
85
+ 11,mlp.down_proj,0.0000218171,0.05000,8.003
86
+ 12,self_attn.k_proj,0.0000009299,0.05000,1.044
87
+ 12,self_attn.v_proj,0.0000010058,0.05000,1.041
88
+ 12,self_attn.q_proj,0.0000054316,0.05000,1.077
89
+ 12,self_attn.o_proj,0.0000024059,0.05000,1.766
90
+ 12,mlp.gate_proj,0.0001412866,0.05000,1.116
91
+ 12,mlp.up_proj,0.0001323689,0.05000,1.117
92
+ 12,mlp.down_proj,0.0000244210,0.05000,7.955
93
+ 13,self_attn.k_proj,0.0000017760,0.05000,1.062
94
+ 13,self_attn.v_proj,0.0000018995,0.05000,1.051
95
+ 13,self_attn.q_proj,0.0000102478,0.05000,1.079
96
+ 13,self_attn.o_proj,0.0000036599,0.05000,1.810
97
+ 13,mlp.gate_proj,0.0001465452,0.05000,1.188
98
+ 13,mlp.up_proj,0.0001332961,0.05000,1.174
99
+ 13,mlp.down_proj,0.0000243287,0.05000,8.004
100
+ 14,self_attn.k_proj,0.0000009200,0.05000,1.052
101
+ 14,self_attn.v_proj,0.0000009821,0.05000,1.049
102
+ 14,self_attn.q_proj,0.0000048295,0.05000,1.076
103
+ 14,self_attn.o_proj,0.0000034132,0.05000,1.790
104
+ 14,mlp.gate_proj,0.0001352126,0.05000,1.166
105
+ 14,mlp.up_proj,0.0001249658,0.05000,1.125
106
+ 14,mlp.down_proj,0.0000223208,0.05000,8.035
107
+ 15,self_attn.k_proj,0.0000008635,0.05000,1.041
108
+ 15,self_attn.v_proj,0.0000009282,0.05000,1.048
109
+ 15,self_attn.q_proj,0.0000051504,0.05000,1.069
110
+ 15,self_attn.o_proj,0.0000034768,0.05000,1.808
111
+ 15,mlp.gate_proj,0.0001202492,0.05000,1.134
112
+ 15,mlp.up_proj,0.0001143246,0.05000,1.126
113
+ 15,mlp.down_proj,0.0000198175,0.05000,7.997
114
+ 16,self_attn.k_proj,0.0000008311,0.05000,1.044
115
+ 16,self_attn.v_proj,0.0000009154,0.05000,1.044
116
+ 16,self_attn.q_proj,0.0000048815,0.05000,1.071
117
+ 16,self_attn.o_proj,0.0000034149,0.05000,1.769
118
+ 16,mlp.gate_proj,0.0001051558,0.05000,1.122
119
+ 16,mlp.up_proj,0.0001000832,0.05000,1.120
120
+ 16,mlp.down_proj,0.0000178747,0.05000,7.986
121
+ 17,self_attn.k_proj,0.0000008668,0.05000,1.065
122
+ 17,self_attn.v_proj,0.0000008656,0.05000,1.034
123
+ 17,self_attn.q_proj,0.0000049575,0.05000,1.060
124
+ 17,self_attn.o_proj,0.0000033593,0.05000,1.801
125
+ 17,mlp.gate_proj,0.0001086903,0.05000,1.307
126
+ 17,mlp.up_proj,0.0001033014,0.05000,1.149
127
+ 17,mlp.down_proj,0.0000185236,0.05000,8.088
128
+ 18,self_attn.k_proj,0.0000011330,0.05000,1.038
129
+ 18,self_attn.v_proj,0.0000011757,0.05000,1.035
130
+ 18,self_attn.q_proj,0.0000066043,0.05000,1.060
131
+ 18,self_attn.o_proj,0.0000032982,0.05000,1.778
132
+ 18,mlp.gate_proj,0.0001154338,0.05000,1.132
133
+ 18,mlp.up_proj,0.0001092103,0.05000,1.119
134
+ 18,mlp.down_proj,0.0000206254,0.05000,8.189
135
+ 19,self_attn.k_proj,0.0000012775,0.05000,1.064
136
+ 19,self_attn.v_proj,0.0000013057,0.05000,1.055
137
+ 19,self_attn.q_proj,0.0000077177,0.05000,1.096
138
+ 19,self_attn.o_proj,0.0000044452,0.05000,1.800
139
+ 19,mlp.gate_proj,0.0001260705,0.05000,1.486
140
+ 19,mlp.up_proj,0.0001200554,0.05000,1.139
141
+ 19,mlp.down_proj,0.0000240489,0.05000,8.030
142
+ 20,self_attn.k_proj,0.0000021487,0.05000,1.063
143
+ 20,self_attn.v_proj,0.0000023166,0.05000,1.042
144
+ 20,self_attn.q_proj,0.0000125007,0.05000,1.071
145
+ 20,self_attn.o_proj,0.0000046935,0.05000,1.767
146
+ 20,mlp.gate_proj,0.0001376763,0.05000,1.140
147
+ 20,mlp.up_proj,0.0001314726,0.05000,1.122
148
+ 20,mlp.down_proj,0.0000271172,0.05000,7.966
149
+ 21,self_attn.k_proj,0.0000024297,0.05000,1.054
150
+ 21,self_attn.v_proj,0.0000025375,0.05000,1.049
151
+ 21,self_attn.q_proj,0.0000141194,0.05000,1.082
152
+ 21,self_attn.o_proj,0.0000085868,0.05000,1.793
153
+ 21,mlp.gate_proj,0.0001451987,0.05000,1.146
154
+ 21,mlp.up_proj,0.0001385588,0.05000,1.146
155
+ 21,mlp.down_proj,0.0000308469,0.05000,8.023
156
+ 22,self_attn.k_proj,0.0000021045,0.05000,1.048
157
+ 22,self_attn.v_proj,0.0000022902,0.05000,1.063
158
+ 22,self_attn.q_proj,0.0000127400,0.05000,1.062
159
+ 22,self_attn.o_proj,0.0000103736,0.05000,1.779
160
+ 22,mlp.gate_proj,0.0001592715,0.05000,1.118
161
+ 22,mlp.up_proj,0.0001518224,0.05000,1.117
162
+ 22,mlp.down_proj,0.0000371563,0.05000,7.971
163
+ 23,self_attn.k_proj,0.0000029360,0.05000,1.048
164
+ 23,self_attn.v_proj,0.0000033406,0.05000,1.038
165
+ 23,self_attn.q_proj,0.0000168955,0.05000,1.065
166
+ 23,self_attn.o_proj,0.0000069991,0.05000,1.822
167
+ 23,mlp.gate_proj,0.0001751471,0.05000,1.119
168
+ 23,mlp.up_proj,0.0001665793,0.05000,1.115
169
+ 23,mlp.down_proj,0.0000446570,0.05000,7.956
170
+ 24,self_attn.k_proj,0.0000052270,0.05000,1.056
171
+ 24,self_attn.v_proj,0.0000058457,0.05000,1.063
172
+ 24,self_attn.q_proj,0.0000323477,0.05000,1.082
173
+ 24,self_attn.o_proj,0.0000152148,0.05000,1.768
174
+ 24,mlp.gate_proj,0.0001969212,0.05000,1.136
175
+ 24,mlp.up_proj,0.0001863398,0.05000,1.122
176
+ 24,mlp.down_proj,0.0000521306,0.05000,8.003
177
+ 25,self_attn.k_proj,0.0000045368,0.05000,1.051
178
+ 25,self_attn.v_proj,0.0000049879,0.05000,1.045
179
+ 25,self_attn.q_proj,0.0000270423,0.05000,1.071
180
+ 25,self_attn.o_proj,0.0000139668,0.05000,1.761
181
+ 25,mlp.gate_proj,0.0002213674,0.05000,1.138
182
+ 25,mlp.up_proj,0.0002081905,0.05000,1.123
183
+ 25,mlp.down_proj,0.0000665647,0.05000,8.044
184
+ 26,self_attn.k_proj,0.0000041029,0.05000,1.053
185
+ 26,self_attn.v_proj,0.0000047737,0.05000,1.059
186
+ 26,self_attn.q_proj,0.0000243842,0.05000,1.070
187
+ 26,self_attn.o_proj,0.0000125715,0.05000,1.760
188
+ 26,mlp.gate_proj,0.0002470852,0.05000,1.130
189
+ 26,mlp.up_proj,0.0002283383,0.05000,1.125
190
+ 26,mlp.down_proj,0.0000837923,0.05000,8.451
191
+ 27,self_attn.k_proj,0.0000060690,0.05000,1.064
192
+ 27,self_attn.v_proj,0.0000072178,0.05000,1.058
193
+ 27,self_attn.q_proj,0.0000348095,0.05000,1.088
194
+ 27,self_attn.o_proj,0.0000136795,0.05000,1.776
195
+ 27,mlp.gate_proj,0.0002878364,0.05000,1.129
196
+ 27,mlp.up_proj,0.0002608704,0.05000,1.129
197
+ 27,mlp.down_proj,0.0001052239,0.05000,8.030
198
+ 28,self_attn.k_proj,0.0000077865,0.05000,1.051
199
+ 28,self_attn.v_proj,0.0000093256,0.05000,1.052
200
+ 28,self_attn.q_proj,0.0000463542,0.05000,1.075
201
+ 28,self_attn.o_proj,0.0000149359,0.05000,1.786
202
+ 28,mlp.gate_proj,0.0003251187,0.05000,1.134
203
+ 28,mlp.up_proj,0.0002960902,0.05000,1.120
204
+ 28,mlp.down_proj,0.0001167624,0.05000,7.985
205
+ 29,self_attn.k_proj,0.0000116028,0.05000,1.046
206
+ 29,self_attn.v_proj,0.0000124041,0.05000,1.043
207
+ 29,self_attn.q_proj,0.0000637293,0.05000,1.073
208
+ 29,self_attn.o_proj,0.0000136918,0.05000,1.772
209
+ 29,mlp.gate_proj,0.0003617665,0.05000,1.127
210
+ 29,mlp.up_proj,0.0003126921,0.05000,1.123
211
+ 29,mlp.down_proj,0.0001199714,0.05000,7.968
212
+ 30,self_attn.k_proj,0.0000238225,0.05000,1.046
213
+ 30,self_attn.v_proj,0.0000317723,0.05000,1.045
214
+ 30,self_attn.q_proj,0.0001267295,0.05000,1.081
215
+ 30,self_attn.o_proj,0.0000166787,0.05000,1.776
216
+ 30,mlp.gate_proj,0.0006058461,0.05000,1.123
217
+ 30,mlp.up_proj,0.0003959458,0.05000,1.121
218
+ 30,mlp.down_proj,0.0001081030,0.05000,8.004
219
+ 31,self_attn.k_proj,0.0000196001,0.05000,1.059
220
+ 31,self_attn.v_proj,0.0000222575,0.05000,1.054
221
+ 31,self_attn.q_proj,0.0001011776,0.05000,1.075
222
+ 31,self_attn.o_proj,0.0000166730,0.05000,1.782
223
+ 31,mlp.gate_proj,0.0010467220,0.05000,1.145
224
+ 31,mlp.up_proj,0.0007263806,0.05000,1.148
225
+ 31,mlp.down_proj,0.0001074331,0.05000,8.376
226
+ 32,self_attn.k_proj,0.0000057730,0.05000,1.069
227
+ 32,self_attn.v_proj,0.0000073269,0.05000,1.055
228
+ 32,self_attn.q_proj,0.0000331176,0.05000,1.088
229
+ 32,self_attn.o_proj,0.0000133086,0.05000,1.784
230
+ 32,mlp.gate_proj,0.0005488825,0.05000,1.131
231
+ 32,mlp.up_proj,0.0003933588,0.05000,1.135
232
+ 32,mlp.down_proj,0.0001048277,0.05000,8.001
233
+ 33,self_attn.k_proj,0.0000048959,0.05000,1.042
234
+ 33,self_attn.v_proj,0.0000050340,0.05000,1.052
235
+ 33,self_attn.q_proj,0.0000268427,0.05000,1.084
236
+ 33,self_attn.o_proj,0.0000099646,0.05000,1.772
237
+ 33,mlp.gate_proj,0.0003607540,0.05000,1.121
238
+ 33,mlp.up_proj,0.0003298347,0.05000,1.118
239
+ 33,mlp.down_proj,0.0001057911,0.05000,7.965
240
+ 34,self_attn.k_proj,0.0000065684,0.05000,1.047
241
+ 34,self_attn.v_proj,0.0000074894,0.05000,1.048
242
+ 34,self_attn.q_proj,0.0000404844,0.05000,1.081
243
+ 34,self_attn.o_proj,0.0000151833,0.05000,1.776
244
+ 34,mlp.gate_proj,0.0003230668,0.05000,1.140
245
+ 34,mlp.up_proj,0.0003079835,0.05000,1.126
246
+ 34,mlp.down_proj,0.0000838736,0.05000,8.001
247
+ 35,self_attn.k_proj,0.0000077875,0.05000,1.044
248
+ 35,self_attn.v_proj,0.0000089657,0.05000,1.038
249
+ 35,self_attn.q_proj,0.0000481206,0.05000,1.079
250
+ 35,self_attn.o_proj,0.0000184487,0.05000,1.764
251
+ 35,mlp.gate_proj,0.0003501297,0.05000,1.120
252
+ 35,mlp.up_proj,0.0003335290,0.05000,1.125
253
+ 35,mlp.down_proj,0.0000936887,0.05000,8.692
254
+ 36,self_attn.k_proj,0.0000049325,0.05000,1.043
255
+ 36,self_attn.v_proj,0.0000056771,0.05000,1.044
256
+ 36,self_attn.q_proj,0.0000304468,0.05000,1.072
257
+ 36,self_attn.o_proj,0.0000143740,0.05000,3.903
258
+ 36,mlp.gate_proj,0.0003720354,0.05000,1.124
259
+ 36,mlp.up_proj,0.0003543600,0.05000,1.118
260
+ 36,mlp.down_proj,0.0001041509,0.05000,8.588
261
+ 37,self_attn.k_proj,0.0000100719,0.05000,1.054
262
+ 37,self_attn.v_proj,0.0000115485,0.05000,1.049
263
+ 37,self_attn.q_proj,0.0000616053,0.05000,1.209
264
+ 37,self_attn.o_proj,0.0000252617,0.05000,1.812
265
+ 37,mlp.gate_proj,0.0003926754,0.05000,1.200
266
+ 37,mlp.up_proj,0.0003614664,0.05000,1.117
267
+ 37,mlp.down_proj,0.0001064732,0.05000,7.987
268
+ 38,self_attn.k_proj,0.0000067528,0.05000,1.065
269
+ 38,self_attn.v_proj,0.0000076714,0.05000,1.060
270
+ 38,self_attn.q_proj,0.0000400771,0.05000,1.181
271
+ 38,self_attn.o_proj,0.0000220664,0.05000,1.787
272
+ 38,mlp.gate_proj,0.0003429898,0.05000,1.140
273
+ 38,mlp.up_proj,0.0003293061,0.05000,1.142
274
+ 38,mlp.down_proj,0.0001008956,0.05000,8.009
275
+ 39,self_attn.k_proj,0.0000061872,0.05000,1.069
276
+ 39,self_attn.v_proj,0.0000065399,0.05000,1.068
277
+ 39,self_attn.q_proj,0.0000380468,0.05000,1.078
278
+ 39,self_attn.o_proj,0.0000231821,0.05000,1.772
279
+ 39,mlp.gate_proj,0.0003072655,0.05000,1.135
280
+ 39,mlp.up_proj,0.0003144672,0.05000,1.128
281
+ 39,mlp.down_proj,0.0000982053,0.05000,8.046
282
+ 40,self_attn.k_proj,0.0000075060,0.05000,1.053
283
+ 40,self_attn.v_proj,0.0000085450,0.05000,1.047
284
+ 40,self_attn.q_proj,0.0000463455,0.05000,1.099
285
+ 40,self_attn.o_proj,0.0000311977,0.05000,1.764
286
+ 40,mlp.gate_proj,0.0002644811,0.05000,1.130
287
+ 40,mlp.up_proj,0.0002856952,0.05000,1.126
288
+ 40,mlp.down_proj,0.0000964624,0.05000,7.991
289
+ 41,self_attn.k_proj,0.0000073851,0.05000,1.042
290
+ 41,self_attn.v_proj,0.0000080522,0.05000,1.045
291
+ 41,self_attn.q_proj,0.0000478026,0.05000,1.070
292
+ 41,self_attn.o_proj,0.0000302376,0.05000,1.768
293
+ 41,mlp.gate_proj,0.0002724422,0.05000,1.130
294
+ 41,mlp.up_proj,0.0002986726,0.05000,1.111
295
+ 41,mlp.down_proj,0.0000970860,0.05000,7.992
296
+ 42,self_attn.k_proj,0.0000100851,0.05000,1.056
297
+ 42,self_attn.v_proj,0.0000115108,0.05000,1.053
298
+ 42,self_attn.q_proj,0.0000662501,0.05000,1.090
299
+ 42,self_attn.o_proj,0.0000333506,0.05000,1.782
300
+ 42,mlp.gate_proj,0.0002813541,0.05000,1.348
301
+ 42,mlp.up_proj,0.0003163875,0.05000,1.161
302
+ 42,mlp.down_proj,0.0001026058,0.05000,8.362
303
+ 43,self_attn.k_proj,0.0000145322,0.05000,1.050
304
+ 43,self_attn.v_proj,0.0000158925,0.05000,1.048
305
+ 43,self_attn.q_proj,0.0000893748,0.05000,1.075
306
+ 43,self_attn.o_proj,0.0000389413,0.05000,1.763
307
+ 43,mlp.gate_proj,0.0003090515,0.05000,1.137
308
+ 43,mlp.up_proj,0.0003404725,0.05000,1.119
309
+ 43,mlp.down_proj,0.0002586559,0.05000,7.994
310
+ 44,self_attn.k_proj,0.0000218219,0.05000,1.054
311
+ 44,self_attn.v_proj,0.0000259004,0.05000,1.055
312
+ 44,self_attn.q_proj,0.0001479396,0.05000,1.077
313
+ 44,self_attn.o_proj,0.0000474695,0.05000,1.783
314
+ 44,mlp.gate_proj,0.0003127389,0.05000,1.128
315
+ 44,mlp.up_proj,0.0003464879,0.05000,1.124
316
+ 44,mlp.down_proj,0.0001232855,0.05000,8.231
317
+ 45,self_attn.k_proj,0.0000227116,0.05000,1.042
318
+ 45,self_attn.v_proj,0.0000225401,0.05000,1.042
319
+ 45,self_attn.q_proj,0.0001326203,0.05000,1.096
320
+ 45,self_attn.o_proj,0.0000609935,0.05000,1.758
321
+ 45,mlp.gate_proj,0.0003154614,0.05000,1.142
322
+ 45,mlp.up_proj,0.0003421955,0.05000,1.125
323
+ 45,mlp.down_proj,0.0001295402,0.05000,8.166
324
+ 46,self_attn.k_proj,0.0000203155,0.05000,1.042
325
+ 46,self_attn.v_proj,0.0000243960,0.05000,1.040
326
+ 46,self_attn.q_proj,0.0001327600,0.05000,1.074
327
+ 46,self_attn.o_proj,0.0000586457,0.05000,1.758
328
+ 46,mlp.gate_proj,0.0003317181,0.05000,1.153
329
+ 46,mlp.up_proj,0.0003596539,0.05000,1.137
330
+ 46,mlp.down_proj,0.0001373474,0.05000,7.975
331
+ 47,self_attn.k_proj,0.0000287401,0.05000,1.059
332
+ 47,self_attn.v_proj,0.0000378734,0.05000,1.049
333
+ 47,self_attn.q_proj,0.0001960034,0.05000,1.094
334
+ 47,self_attn.o_proj,0.0000479580,0.05000,1.804
335
+ 47,mlp.gate_proj,0.0003378080,0.05000,1.130
336
+ 47,mlp.up_proj,0.0003639913,0.05000,1.130
337
+ 47,mlp.down_proj,0.0001630509,0.05000,8.682
338
+ 48,self_attn.k_proj,0.0000326587,0.05000,1.070
339
+ 48,self_attn.v_proj,0.0000420830,0.05000,1.069
340
+ 48,self_attn.q_proj,0.0002336485,0.05000,1.089
341
+ 48,self_attn.o_proj,0.0000797854,0.05000,1.795
342
+ 48,mlp.gate_proj,0.0003719960,0.05000,1.677
343
+ 48,mlp.up_proj,0.0003905721,0.05000,1.151
344
+ 48,mlp.down_proj,0.0001752929,0.05000,8.103
345
+ 49,self_attn.k_proj,0.0000346826,0.05000,1.048
346
+ 49,self_attn.v_proj,0.0000406586,0.05000,1.054
347
+ 49,self_attn.q_proj,0.0002300940,0.05000,1.088
348
+ 49,self_attn.o_proj,0.0000726788,0.05000,1.775
349
+ 49,mlp.gate_proj,0.0004289962,0.05000,1.136
350
+ 49,mlp.up_proj,0.0004409457,0.05000,1.132
351
+ 49,mlp.down_proj,0.0002485424,0.05000,7.970
352
+ 50,self_attn.k_proj,0.0000364574,0.05000,1.051
353
+ 50,self_attn.v_proj,0.0000476124,0.05000,1.045
354
+ 50,self_attn.q_proj,0.0002595472,0.05000,1.078
355
+ 50,self_attn.o_proj,0.0000738570,0.05000,1.797
356
+ 50,mlp.gate_proj,0.0005196592,0.05000,1.125
357
+ 50,mlp.up_proj,0.0005209628,0.05000,1.130
358
+ 50,mlp.down_proj,0.0004004640,0.05000,8.063
359
+ 51,self_attn.k_proj,0.0000649455,0.05000,1.057
360
+ 51,self_attn.v_proj,0.0000829220,0.05000,1.049
361
+ 51,self_attn.q_proj,0.0004398252,0.05000,1.087
362
+ 51,self_attn.o_proj,0.0001423696,0.05000,1.797
363
+ 51,mlp.gate_proj,0.0006647636,0.05000,1.153
364
+ 51,mlp.up_proj,0.0006608297,0.05000,1.152
365
+ 51,mlp.down_proj,0.0006123469,0.05000,8.000
366
+ 52,self_attn.k_proj,0.0000878023,0.05000,1.052
367
+ 52,self_attn.v_proj,0.0001286716,0.05000,1.054
368
+ 52,self_attn.q_proj,0.0006764697,0.05000,1.099
369
+ 52,self_attn.o_proj,0.0001523513,0.05000,1.782
370
+ 52,mlp.gate_proj,0.0008464120,0.05000,1.124
371
+ 52,mlp.up_proj,0.0008526947,0.05000,1.126
372
+ 52,mlp.down_proj,0.0008183107,0.05000,8.027
373
+ 53,self_attn.k_proj,0.0001403411,0.05000,1.042
374
+ 53,self_attn.v_proj,0.0001782136,0.05000,1.037
375
+ 53,self_attn.q_proj,0.0009704368,0.05000,1.250
376
+ 53,self_attn.o_proj,0.0001480780,0.05000,1.917
377
+ 53,mlp.gate_proj,0.0009788685,0.05000,1.131
378
+ 53,mlp.up_proj,0.0009995223,0.05000,1.134
379
+ 53,mlp.down_proj,0.0012458582,0.05000,8.069
380
+ 54,self_attn.k_proj,0.0002222697,0.05000,1.056
381
+ 54,self_attn.v_proj,0.0003150965,0.05000,1.046
382
+ 54,self_attn.q_proj,0.0015428386,0.05000,1.074
383
+ 54,self_attn.o_proj,0.0002995660,0.05000,1.815
384
+ 54,mlp.gate_proj,0.0013180814,0.05000,1.135
385
+ 54,mlp.up_proj,0.0013410654,0.05000,1.134
386
+ 54,mlp.down_proj,0.0016283727,0.05000,7.964
387
+ 55,self_attn.k_proj,0.0002455719,0.05000,1.062
388
+ 55,self_attn.v_proj,0.0002898146,0.05000,1.053
389
+ 55,self_attn.q_proj,0.0016511303,0.05000,1.080
390
+ 55,self_attn.o_proj,0.0002813179,0.05000,1.794
391
+ 55,mlp.gate_proj,0.0014898408,0.05000,1.446
392
+ 55,mlp.up_proj,0.0015437358,0.05000,1.134
393
+ 55,mlp.down_proj,0.0021947372,0.05000,8.029
394
+ 56,self_attn.k_proj,0.0004278187,0.05000,1.041
395
+ 56,self_attn.v_proj,0.0006316985,0.05000,1.039
396
+ 56,self_attn.q_proj,0.0029827804,0.05000,1.061
397
+ 56,self_attn.o_proj,0.0003085413,0.05000,1.788
398
+ 56,mlp.gate_proj,0.0017243970,0.05000,1.164
399
+ 56,mlp.up_proj,0.0018149042,0.05000,1.149
400
+ 56,mlp.down_proj,0.0027739530,0.05000,8.076
401
+ 57,self_attn.k_proj,0.0005359473,0.05000,1.052
402
+ 57,self_attn.v_proj,0.0008049904,0.05000,1.044
403
+ 57,self_attn.q_proj,0.0038959943,0.05000,1.090
404
+ 57,self_attn.o_proj,0.0003918819,0.05000,1.765
405
+ 57,mlp.gate_proj,0.0018884934,0.05000,1.139
406
+ 57,mlp.up_proj,0.0020396879,0.05000,1.125
407
+ 57,mlp.down_proj,0.0037069661,0.05000,7.999
408
+ 58,self_attn.k_proj,0.0008708814,0.05000,1.038
409
+ 58,self_attn.v_proj,0.0013238839,0.05000,1.060
410
+ 58,self_attn.q_proj,0.0062347704,0.05000,1.074
411
+ 58,self_attn.o_proj,0.0004224728,0.05000,1.770
412
+ 58,mlp.gate_proj,0.0021498542,0.05000,1.140
413
+ 58,mlp.up_proj,0.0023638556,0.05000,1.122
414
+ 58,mlp.down_proj,0.0048660359,0.05000,8.354
415
+ 59,self_attn.k_proj,0.0010695715,0.05000,1.045
416
+ 59,self_attn.v_proj,0.0017025579,0.05000,1.064
417
+ 59,self_attn.q_proj,0.0078237816,0.05000,1.083
418
+ 59,self_attn.o_proj,0.0004261862,0.05000,1.775
419
+ 59,mlp.gate_proj,0.0023862109,0.05000,1.255
420
+ 59,mlp.up_proj,0.0026503182,0.05000,1.144
421
+ 59,mlp.down_proj,0.0074393693,0.05000,8.122
422
+ 60,self_attn.k_proj,0.0011864857,0.05000,1.072
423
+ 60,self_attn.v_proj,0.0017836547,0.05000,1.071
424
+ 60,self_attn.q_proj,0.0079164522,0.05000,1.096
425
+ 60,self_attn.o_proj,0.0012012388,0.05000,1.808
426
+ 60,mlp.gate_proj,0.0025860246,0.05000,1.145
427
+ 60,mlp.up_proj,0.0029487530,0.05000,1.143
428
+ 60,mlp.down_proj,0.0112182335,0.05000,8.058
429
+ 61,self_attn.k_proj,0.0015718682,0.05000,1.049
430
+ 61,self_attn.v_proj,0.0026914134,0.05000,1.048
431
+ 61,self_attn.q_proj,0.0114342334,0.05000,1.076
432
+ 61,self_attn.o_proj,0.0012516713,0.05000,1.786
433
+ 61,mlp.gate_proj,0.0027420398,0.05000,1.126
434
+ 61,mlp.up_proj,0.0031601495,0.05000,1.142
435
+ 61,mlp.down_proj,0.0159969039,0.05000,7.986
436
+ 62,self_attn.k_proj,0.0016475655,0.05000,1.066
437
+ 62,self_attn.v_proj,0.0028598230,0.05000,1.049
438
+ 62,self_attn.q_proj,0.0114434291,0.05000,1.073
439
+ 62,self_attn.o_proj,0.0022906732,0.05000,1.797
440
+ 62,mlp.gate_proj,0.0033809583,0.05000,1.133
441
+ 62,mlp.up_proj,0.0037481985,0.05000,1.126
442
+ 62,mlp.down_proj,0.0255297494,0.05000,8.035
443
+ 63,self_attn.k_proj,0.0007640351,0.05000,1.059
444
+ 63,self_attn.v_proj,0.0011615969,0.05000,1.046
445
+ 63,self_attn.q_proj,0.0052693927,0.05000,1.076
446
+ 63,self_attn.o_proj,0.0020771761,0.05000,1.768
447
+ 63,mlp.gate_proj,0.0041764780,0.05000,1.125
448
+ 63,mlp.up_proj,0.0045288563,0.05000,1.131
449
+ 63,mlp.down_proj,0.0907532932,0.05000,8.077
quantize_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
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