JunHowie commited on
Commit
fa6b8f7
·
verified ·
1 Parent(s): fb8a6b5

Add files using upload-large-folder tool

Browse files
.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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 29568,
13
+ "layer_types": [
14
+ "full_attention",
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
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention"
94
+ ],
95
+ "max_position_embeddings": 131072,
96
+ "max_window_layers": 70,
97
+ "model_type": "qwen2",
98
+ "num_attention_heads": 64,
99
+ "num_hidden_layers": 80,
100
+ "num_key_value_heads": 8,
101
+ "quantization_config": {
102
+ "bits": 8,
103
+ "checkpoint_format": "gptq",
104
+ "desc_act": false,
105
+ "group_size": 128,
106
+ "lm_head": false,
107
+ "meta": {
108
+ "act_group_aware": false,
109
+ "damp_auto_increment": 0.01,
110
+ "damp_percent": 0.05,
111
+ "mse": 0.0,
112
+ "quantizer": [
113
+ "gptqmodel:4.2.5"
114
+ ],
115
+ "static_groups": false,
116
+ "true_sequential": true,
117
+ "uri": "https://github.com/modelcloud/gptqmodel",
118
+ "v2": false,
119
+ "v2_alpha": 0.25
120
+ },
121
+ "pack_dtype": "int32",
122
+ "quant_method": "gptq",
123
+ "sym": true
124
+ },
125
+ "rms_norm_eps": 1e-06,
126
+ "rope_scaling": null,
127
+ "rope_theta": 1000000.0,
128
+ "sliding_window": null,
129
+ "tie_word_embeddings": false,
130
+ "transformers_version": "4.56.2",
131
+ "use_cache": true,
132
+ "use_sliding_window": false,
133
+ "vocab_size": 152064
134
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.56.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c806c0c18012e4c1f8063c1bcbcee18f5947a4201918b70d68c552be3f0a9d
3
+ size 3792635632
model-00002-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108f5026446837b3fd1942de8bff2841579c5d2d9c73e6edfbeb27f9deada065
3
+ size 3842331544
model-00003-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20abdbadf0a5513eda50f8a0007df2a5ec4fa2c7fab70b44d4ee5ec4e6da2a76
3
+ size 3997137624
model-00004-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c813d78ff8faa0ed3c76e4a5cdca4a519066ea526d3ce197a56a7ea434e6af
3
+ size 3842331688
model-00005-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01eefbe80ef2b55d454e7f5ac0cf36e898c29278d0ba882f37cd39c0ecfda98d
3
+ size 3842331680
model-00006-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4438f36c5905d1c62fffae58073a9dd21f1300158ce8be7cc8028fa748f2beef
3
+ size 3997137792
model-00007-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7af4cd6088c8ab112bb8a7e92e6818b9ec725e958d24215060b0163dad4e146
3
+ size 3842331688
model-00008-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4042467c4570ca3c9a380f4fd5089fec45af83d21c684d07fdc08197fd37281
3
+ size 3842331680
model-00009-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72156bd032b24818f6375739d7e2c6e2dfc36a0ac6ae2da81810b69e6427fa28
3
+ size 3997137792
model-00010-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443a3485c9eeb0f15b9e4bcd5b754d2d109a1f1795c035c9cda2330bd5a1a570
3
+ size 3842331688
model-00011-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777032e5152a591414f7d751d1c7876352a2b588079b46c229b6963e8c6e94e4
3
+ size 3842331680
model-00012-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccf3f2576ceb8b7fb671addafe8ee16120933ac997c07c8ec20976447046159
3
+ size 3997137792
model-00013-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a275158ef212851d8397ca3b0e6fc5044edca0ebddb4edffcf321880f0058c
3
+ size 3842331688
model-00014-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58872422b99b71a73e9758b4b24f6ec53b38ad078011467ca4dbdd99c2ff639e
3
+ size 3842331680
model-00015-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2197fa49cfa52ce161e68a5fa3b52b511bf20ccc2cc3d00f6c9b7ad4434da45
3
+ size 3997137792
model-00016-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34093b505919745ad92555cecebfb372fbf9ac5445aad42c904be21f96832fcb
3
+ size 3842331688
model-00017-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a356a1772529291c7019d513bd588aea02ea528cfad6a954b5658ce6951055
3
+ size 3842331680
model-00018-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5016e06dee604a5abd08b73ea8bd6f725021dac4b36b77a0ce6582a0ffabd4f
3
+ size 3997137792
model-00019-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40ceb08dce46a3894ce12278b79e94d9b9d0f7d8c287e0cedfbb4d3f29af090
3
+ size 3842331688
model-00020-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a135c66f87a189c625c9a64d583135136bfe6eb8bf1baa06fc09e9a241f6b3c
3
+ size 2987414320
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quant_log.csv ADDED
@@ -0,0 +1,561 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.0000000002,0.05000,1.974
3
+ 0,self_attn.v_proj,0.0000000000,0.05000,1.669
4
+ 0,self_attn.q_proj,0.0000000012,0.05000,1.729
5
+ 0,self_attn.o_proj,0.0000000000,0.05000,1.706
6
+ 0,mlp.gate_proj,0.0000000007,0.05000,1.914
7
+ 0,mlp.up_proj,0.0000000007,0.05000,1.880
8
+ 0,mlp.down_proj,0.0000000000,0.05000,10.259
9
+ 1,self_attn.k_proj,0.0000000001,0.05000,1.658
10
+ 1,self_attn.v_proj,0.0000000000,0.05000,1.652
11
+ 1,self_attn.q_proj,0.0000000005,0.05000,1.732
12
+ 1,self_attn.o_proj,0.0000000000,0.05000,1.723
13
+ 1,mlp.gate_proj,0.0000000023,0.05000,1.906
14
+ 1,mlp.up_proj,0.0000000021,0.05000,1.898
15
+ 1,mlp.down_proj,0.0000008961,0.05000,10.304
16
+ 2,self_attn.k_proj,0.0000000072,0.05000,1.720
17
+ 2,self_attn.v_proj,0.0000000027,0.05000,1.684
18
+ 2,self_attn.q_proj,0.0000000268,0.05000,2.013
19
+ 2,self_attn.o_proj,0.0000000000,0.05000,1.745
20
+ 2,mlp.gate_proj,0.0000000038,0.05000,1.935
21
+ 2,mlp.up_proj,0.0000000036,0.05000,1.910
22
+ 2,mlp.down_proj,0.0000000001,0.05000,10.370
23
+ 3,self_attn.k_proj,0.0000000051,0.05000,1.693
24
+ 3,self_attn.v_proj,0.0000000022,0.05000,1.675
25
+ 3,self_attn.q_proj,0.0000000180,0.05000,1.742
26
+ 3,self_attn.o_proj,0.0000000001,0.05000,1.779
27
+ 3,mlp.gate_proj,0.0000000063,0.05000,1.927
28
+ 3,mlp.up_proj,0.0000000062,0.05000,1.915
29
+ 3,mlp.down_proj,0.0000000001,0.05000,10.372
30
+ 4,self_attn.k_proj,0.0000000074,0.05000,1.671
31
+ 4,self_attn.v_proj,0.0000000038,0.05000,1.646
32
+ 4,self_attn.q_proj,0.0000000315,0.05000,1.723
33
+ 4,self_attn.o_proj,0.0000000000,0.05000,1.728
34
+ 4,mlp.gate_proj,0.0000000122,0.05000,1.911
35
+ 4,mlp.up_proj,0.0000000119,0.05000,1.907
36
+ 4,mlp.down_proj,0.0000000002,0.05000,10.358
37
+ 5,self_attn.k_proj,0.0000000103,0.05000,1.671
38
+ 5,self_attn.v_proj,0.0000000059,0.05000,1.673
39
+ 5,self_attn.q_proj,0.0000000424,0.05000,1.719
40
+ 5,self_attn.o_proj,0.0000000000,0.05000,1.733
41
+ 5,mlp.gate_proj,0.0000000204,0.05000,1.899
42
+ 5,mlp.up_proj,0.0000000196,0.05000,1.896
43
+ 5,mlp.down_proj,0.0000000005,0.05000,10.346
44
+ 6,self_attn.k_proj,0.0000000069,0.05000,1.679
45
+ 6,self_attn.v_proj,0.0000000038,0.05000,1.696
46
+ 6,self_attn.q_proj,0.0000000270,0.05000,1.797
47
+ 6,self_attn.o_proj,0.0000000000,0.05000,1.755
48
+ 6,mlp.gate_proj,0.0000000274,0.05000,1.951
49
+ 6,mlp.up_proj,0.0000000263,0.05000,1.917
50
+ 6,mlp.down_proj,0.0000000007,0.05000,10.348
51
+ 7,self_attn.k_proj,0.0000000097,0.05000,1.676
52
+ 7,self_attn.v_proj,0.0000000049,0.05000,1.670
53
+ 7,self_attn.q_proj,0.0000000391,0.05000,1.870
54
+ 7,self_attn.o_proj,0.0000000001,0.05000,1.739
55
+ 7,mlp.gate_proj,0.0000000347,0.05000,2.106
56
+ 7,mlp.up_proj,0.0000000336,0.05000,1.917
57
+ 7,mlp.down_proj,0.0000000008,0.05000,10.379
58
+ 8,self_attn.k_proj,0.0000000091,0.05000,1.696
59
+ 8,self_attn.v_proj,0.0000000049,0.05000,1.691
60
+ 8,self_attn.q_proj,0.0000000357,0.05000,1.749
61
+ 8,self_attn.o_proj,0.0000000003,0.05000,1.743
62
+ 8,mlp.gate_proj,0.0000000405,0.05000,1.952
63
+ 8,mlp.up_proj,0.0000000386,0.05000,1.928
64
+ 8,mlp.down_proj,0.0000000011,0.05000,10.429
65
+ 9,self_attn.k_proj,0.0000000248,0.05000,1.686
66
+ 9,self_attn.v_proj,0.0000000147,0.05000,1.678
67
+ 9,self_attn.q_proj,0.0000001123,0.05000,1.757
68
+ 9,self_attn.o_proj,0.0000000005,0.05000,1.750
69
+ 9,mlp.gate_proj,0.0000000437,0.05000,1.930
70
+ 9,mlp.up_proj,0.0000000421,0.05000,1.922
71
+ 9,mlp.down_proj,0.0000000012,0.05000,10.380
72
+ 10,self_attn.k_proj,0.0000000149,0.05000,1.832
73
+ 10,self_attn.v_proj,0.0000000078,0.05000,1.673
74
+ 10,self_attn.q_proj,0.0000000632,0.05000,1.762
75
+ 10,self_attn.o_proj,0.0000000006,0.05000,1.745
76
+ 10,mlp.gate_proj,0.0000000530,0.05000,1.930
77
+ 10,mlp.up_proj,0.0000000508,0.05000,1.924
78
+ 10,mlp.down_proj,0.0000000016,0.05000,10.373
79
+ 11,self_attn.k_proj,0.0000000174,0.05000,1.683
80
+ 11,self_attn.v_proj,0.0000000082,0.05000,1.680
81
+ 11,self_attn.q_proj,0.0000000763,0.05000,1.740
82
+ 11,self_attn.o_proj,0.0000000007,0.05000,1.737
83
+ 11,mlp.gate_proj,0.0000000608,0.05000,1.929
84
+ 11,mlp.up_proj,0.0000000578,0.05000,1.922
85
+ 11,mlp.down_proj,0.0000000021,0.05000,10.403
86
+ 12,self_attn.k_proj,0.0000000232,0.05000,1.685
87
+ 12,self_attn.v_proj,0.0000000127,0.05000,1.680
88
+ 12,self_attn.q_proj,0.0000001077,0.05000,1.734
89
+ 12,self_attn.o_proj,0.0000000010,0.05000,1.739
90
+ 12,mlp.gate_proj,0.0000000679,0.05000,1.916
91
+ 12,mlp.up_proj,0.0000000650,0.05000,1.903
92
+ 12,mlp.down_proj,0.0000000024,0.05000,10.544
93
+ 13,self_attn.k_proj,0.0000000216,0.05000,1.725
94
+ 13,self_attn.v_proj,0.0000000119,0.05000,1.682
95
+ 13,self_attn.q_proj,0.0000000984,0.05000,1.740
96
+ 13,self_attn.o_proj,0.0000000008,0.05000,1.740
97
+ 13,mlp.gate_proj,0.0000000776,0.05000,1.928
98
+ 13,mlp.up_proj,0.0000000744,0.05000,1.916
99
+ 13,mlp.down_proj,0.0000000031,0.05000,10.419
100
+ 14,self_attn.k_proj,0.0000000208,0.05000,1.681
101
+ 14,self_attn.v_proj,0.0000000114,0.05000,1.667
102
+ 14,self_attn.q_proj,0.0000000948,0.05000,1.726
103
+ 14,self_attn.o_proj,0.0000000014,0.05000,1.732
104
+ 14,mlp.gate_proj,0.0000000797,0.05000,1.936
105
+ 14,mlp.up_proj,0.0000000766,0.05000,1.910
106
+ 14,mlp.down_proj,0.0000000034,0.05000,10.375
107
+ 15,self_attn.k_proj,0.0000000260,0.05000,1.708
108
+ 15,self_attn.v_proj,0.0000000144,0.05000,1.686
109
+ 15,self_attn.q_proj,0.0000001285,0.05000,1.740
110
+ 15,self_attn.o_proj,0.0000000011,0.05000,1.739
111
+ 15,mlp.gate_proj,0.0000001000,0.05000,1.947
112
+ 15,mlp.up_proj,0.0000000956,0.05000,1.984
113
+ 15,mlp.down_proj,0.0000000041,0.05000,10.378
114
+ 16,self_attn.k_proj,0.0000000244,0.05000,1.702
115
+ 16,self_attn.v_proj,0.0000000126,0.05000,1.695
116
+ 16,self_attn.q_proj,0.0000001144,0.05000,1.765
117
+ 16,self_attn.o_proj,0.0000000013,0.05000,1.739
118
+ 16,mlp.gate_proj,0.0000001086,0.05000,1.921
119
+ 16,mlp.up_proj,0.0000001038,0.05000,1.909
120
+ 16,mlp.down_proj,0.0000000048,0.05000,10.561
121
+ 17,self_attn.k_proj,0.0000000198,0.05000,1.673
122
+ 17,self_attn.v_proj,0.0000000121,0.05000,1.671
123
+ 17,self_attn.q_proj,0.0000000910,0.05000,1.734
124
+ 17,self_attn.o_proj,0.0000000017,0.05000,1.725
125
+ 17,mlp.gate_proj,0.0000001043,0.05000,1.907
126
+ 17,mlp.up_proj,0.0000001004,0.05000,1.907
127
+ 17,mlp.down_proj,0.0000000052,0.05000,10.344
128
+ 18,self_attn.k_proj,0.0000000385,0.05000,2.049
129
+ 18,self_attn.v_proj,0.0000000218,0.05000,1.699
130
+ 18,self_attn.q_proj,0.0000001757,0.05000,1.776
131
+ 18,self_attn.o_proj,0.0000000015,0.05000,1.755
132
+ 18,mlp.gate_proj,0.0000001256,0.05000,1.967
133
+ 18,mlp.up_proj,0.0000001200,0.05000,1.908
134
+ 18,mlp.down_proj,0.0000000065,0.05000,10.347
135
+ 19,self_attn.k_proj,0.0000000501,0.05000,1.685
136
+ 19,self_attn.v_proj,0.0000000309,0.05000,1.691
137
+ 19,self_attn.q_proj,0.0000002407,0.05000,1.745
138
+ 19,self_attn.o_proj,0.0000000016,0.05000,1.737
139
+ 19,mlp.gate_proj,0.0000001447,0.05000,2.317
140
+ 19,mlp.up_proj,0.0000001387,0.05000,1.923
141
+ 19,mlp.down_proj,0.0000000093,0.05000,10.378
142
+ 20,self_attn.k_proj,0.0000000189,0.05000,1.693
143
+ 20,self_attn.v_proj,0.0000000115,0.05000,1.674
144
+ 20,self_attn.q_proj,0.0000000936,0.05000,2.097
145
+ 20,self_attn.o_proj,0.0000000022,0.05000,1.745
146
+ 20,mlp.gate_proj,0.0000001753,0.05000,1.931
147
+ 20,mlp.up_proj,0.0000001662,0.05000,1.917
148
+ 20,mlp.down_proj,0.0000000123,0.05000,10.487
149
+ 21,self_attn.k_proj,0.0000000155,0.05000,1.669
150
+ 21,self_attn.v_proj,0.0000000104,0.05000,1.688
151
+ 21,self_attn.q_proj,0.0000000778,0.05000,1.737
152
+ 21,self_attn.o_proj,0.0000000039,0.05000,1.738
153
+ 21,mlp.gate_proj,0.0000001586,0.05000,1.919
154
+ 21,mlp.up_proj,0.0000001516,0.05000,1.907
155
+ 21,mlp.down_proj,0.0000000121,0.05000,10.398
156
+ 22,self_attn.k_proj,0.0000000406,0.05000,1.930
157
+ 22,self_attn.v_proj,0.0000000258,0.05000,1.795
158
+ 22,self_attn.q_proj,0.0000002221,0.05000,1.847
159
+ 22,self_attn.o_proj,0.0000000047,0.05000,1.845
160
+ 22,mlp.gate_proj,0.0000002180,0.05000,1.908
161
+ 22,mlp.up_proj,0.0000002092,0.05000,1.899
162
+ 22,mlp.down_proj,0.0000000232,0.05000,10.346
163
+ 23,self_attn.k_proj,0.0000000330,0.05000,1.688
164
+ 23,self_attn.v_proj,0.0000000227,0.05000,1.694
165
+ 23,self_attn.q_proj,0.0000001895,0.05000,1.735
166
+ 23,self_attn.o_proj,0.0000000058,0.05000,1.731
167
+ 23,mlp.gate_proj,0.0000002436,0.05000,2.232
168
+ 23,mlp.up_proj,0.0000002310,0.05000,1.919
169
+ 23,mlp.down_proj,0.0000000223,0.05000,10.404
170
+ 24,self_attn.k_proj,0.0000000284,0.05000,1.704
171
+ 24,self_attn.v_proj,0.0000000233,0.05000,1.677
172
+ 24,self_attn.q_proj,0.0000001599,0.05000,1.756
173
+ 24,self_attn.o_proj,0.0000000056,0.05000,1.740
174
+ 24,mlp.gate_proj,0.0000002843,0.05000,1.914
175
+ 24,mlp.up_proj,0.0000002675,0.05000,1.923
176
+ 24,mlp.down_proj,0.0000000246,0.05000,10.306
177
+ 25,self_attn.k_proj,0.0000000507,0.05000,1.685
178
+ 25,self_attn.v_proj,0.0000000330,0.05000,1.658
179
+ 25,self_attn.q_proj,0.0000002889,0.05000,1.731
180
+ 25,self_attn.o_proj,0.0000000067,0.05000,1.731
181
+ 25,mlp.gate_proj,0.0000003367,0.05000,1.912
182
+ 25,mlp.up_proj,0.0000003191,0.05000,1.902
183
+ 25,mlp.down_proj,0.0000000288,0.05000,10.478
184
+ 26,self_attn.k_proj,0.0000000367,0.05000,1.930
185
+ 26,self_attn.v_proj,0.0000000248,0.05000,1.656
186
+ 26,self_attn.q_proj,0.0000002028,0.05000,1.726
187
+ 26,self_attn.o_proj,0.0000000083,0.05000,1.722
188
+ 26,mlp.gate_proj,0.0000003796,0.05000,1.905
189
+ 26,mlp.up_proj,0.0000003608,0.05000,1.904
190
+ 26,mlp.down_proj,0.0000000304,0.05000,10.362
191
+ 27,self_attn.k_proj,0.0000000365,0.05000,1.719
192
+ 27,self_attn.v_proj,0.0000000260,0.05000,1.680
193
+ 27,self_attn.q_proj,0.0000001969,0.05000,1.739
194
+ 27,self_attn.o_proj,0.0000000069,0.05000,1.726
195
+ 27,mlp.gate_proj,0.0000004164,0.05000,1.978
196
+ 27,mlp.up_proj,0.0000003971,0.05000,1.906
197
+ 27,mlp.down_proj,0.0000000330,0.05000,10.315
198
+ 28,self_attn.k_proj,0.0000000359,0.05000,1.672
199
+ 28,self_attn.v_proj,0.0000000281,0.05000,1.661
200
+ 28,self_attn.q_proj,0.0000002018,0.05000,1.720
201
+ 28,self_attn.o_proj,0.0000000056,0.05000,1.825
202
+ 28,mlp.gate_proj,0.0000004448,0.05000,1.915
203
+ 28,mlp.up_proj,0.0000004269,0.05000,1.922
204
+ 28,mlp.down_proj,0.0000000380,0.05000,10.441
205
+ 29,self_attn.k_proj,0.0000000469,0.05000,1.686
206
+ 29,self_attn.v_proj,0.0000000308,0.05000,1.671
207
+ 29,self_attn.q_proj,0.0000002493,0.05000,1.732
208
+ 29,self_attn.o_proj,0.0000000091,0.05000,1.749
209
+ 29,mlp.gate_proj,0.0000004729,0.05000,1.929
210
+ 29,mlp.up_proj,0.0000004529,0.05000,1.907
211
+ 29,mlp.down_proj,0.0000000403,0.05000,10.360
212
+ 30,self_attn.k_proj,0.0000000461,0.05000,1.996
213
+ 30,self_attn.v_proj,0.0000000365,0.05000,1.671
214
+ 30,self_attn.q_proj,0.0000002671,0.05000,1.728
215
+ 30,self_attn.o_proj,0.0000000104,0.05000,1.738
216
+ 30,mlp.gate_proj,0.0000005154,0.05000,1.914
217
+ 30,mlp.up_proj,0.0000004883,0.05000,1.904
218
+ 30,mlp.down_proj,0.0000000424,0.05000,10.348
219
+ 31,self_attn.k_proj,0.0000000515,0.05000,1.688
220
+ 31,self_attn.v_proj,0.0000000394,0.05000,1.672
221
+ 31,self_attn.q_proj,0.0000002855,0.05000,1.712
222
+ 31,self_attn.o_proj,0.0000000071,0.05000,1.710
223
+ 31,mlp.gate_proj,0.0000005588,0.05000,1.907
224
+ 31,mlp.up_proj,0.0000005285,0.05000,1.895
225
+ 31,mlp.down_proj,0.0000000449,0.05000,10.287
226
+ 32,self_attn.k_proj,0.0000000566,0.05000,1.686
227
+ 32,self_attn.v_proj,0.0000000439,0.05000,1.661
228
+ 32,self_attn.q_proj,0.0000003142,0.05000,1.719
229
+ 32,self_attn.o_proj,0.0000000082,0.05000,1.721
230
+ 32,mlp.gate_proj,0.0000005844,0.05000,1.927
231
+ 32,mlp.up_proj,0.0000005537,0.05000,1.907
232
+ 32,mlp.down_proj,0.0000000477,0.05000,10.363
233
+ 33,self_attn.k_proj,0.0000000530,0.05000,1.695
234
+ 33,self_attn.v_proj,0.0000000485,0.05000,1.689
235
+ 33,self_attn.q_proj,0.0000002834,0.05000,1.735
236
+ 33,self_attn.o_proj,0.0000000060,0.05000,1.739
237
+ 33,mlp.gate_proj,0.0000006227,0.05000,1.919
238
+ 33,mlp.up_proj,0.0000005820,0.05000,1.914
239
+ 33,mlp.down_proj,0.0000000490,0.05000,10.298
240
+ 34,self_attn.k_proj,0.0000000596,0.05000,1.676
241
+ 34,self_attn.v_proj,0.0000000547,0.05000,1.676
242
+ 34,self_attn.q_proj,0.0000003310,0.05000,1.717
243
+ 34,self_attn.o_proj,0.0000000044,0.05000,1.729
244
+ 34,mlp.gate_proj,0.0000006503,0.05000,1.912
245
+ 34,mlp.up_proj,0.0000006064,0.05000,1.900
246
+ 34,mlp.down_proj,0.0000000523,0.05000,10.422
247
+ 35,self_attn.k_proj,0.0000000653,0.05000,1.674
248
+ 35,self_attn.v_proj,0.0000000614,0.05000,1.683
249
+ 35,self_attn.q_proj,0.0000003620,0.05000,2.377
250
+ 35,self_attn.o_proj,0.0000000036,0.05000,1.718
251
+ 35,mlp.gate_proj,0.0000006651,0.05000,1.926
252
+ 35,mlp.up_proj,0.0000006244,0.05000,1.910
253
+ 35,mlp.down_proj,0.0000000536,0.05000,10.552
254
+ 36,self_attn.k_proj,0.0000000689,0.05000,1.658
255
+ 36,self_attn.v_proj,0.0000000649,0.05000,1.657
256
+ 36,self_attn.q_proj,0.0000003802,0.05000,1.706
257
+ 36,self_attn.o_proj,0.0000000064,0.05000,1.718
258
+ 36,mlp.gate_proj,0.0000006757,0.05000,1.931
259
+ 36,mlp.up_proj,0.0000006380,0.05000,1.894
260
+ 36,mlp.down_proj,0.0000000534,0.05000,10.309
261
+ 37,self_attn.k_proj,0.0000000654,0.05000,1.668
262
+ 37,self_attn.v_proj,0.0000000588,0.05000,1.662
263
+ 37,self_attn.q_proj,0.0000003550,0.05000,1.710
264
+ 37,self_attn.o_proj,0.0000000057,0.05000,1.733
265
+ 37,mlp.gate_proj,0.0000006918,0.05000,2.328
266
+ 37,mlp.up_proj,0.0000006588,0.05000,1.934
267
+ 37,mlp.down_proj,0.0000000565,0.05000,10.372
268
+ 38,self_attn.k_proj,0.0000000652,0.05000,1.686
269
+ 38,self_attn.v_proj,0.0000000540,0.05000,1.697
270
+ 38,self_attn.q_proj,0.0000003431,0.05000,1.736
271
+ 38,self_attn.o_proj,0.0000000096,0.05000,1.741
272
+ 38,mlp.gate_proj,0.0000007154,0.05000,1.921
273
+ 38,mlp.up_proj,0.0000006809,0.05000,1.929
274
+ 38,mlp.down_proj,0.0000000597,0.05000,10.366
275
+ 39,self_attn.k_proj,0.0000000628,0.05000,1.715
276
+ 39,self_attn.v_proj,0.0000000543,0.05000,1.686
277
+ 39,self_attn.q_proj,0.0000003293,0.05000,1.742
278
+ 39,self_attn.o_proj,0.0000000088,0.05000,1.726
279
+ 39,mlp.gate_proj,0.0000007348,0.05000,1.888
280
+ 39,mlp.up_proj,0.0000007033,0.05000,1.889
281
+ 39,mlp.down_proj,0.0000000644,0.05000,10.275
282
+ 40,self_attn.k_proj,0.0000000626,0.05000,1.658
283
+ 40,self_attn.v_proj,0.0000000444,0.05000,1.652
284
+ 40,self_attn.q_proj,0.0000003235,0.05000,1.708
285
+ 40,self_attn.o_proj,0.0000000141,0.05000,1.716
286
+ 40,mlp.gate_proj,0.0000007610,0.05000,1.901
287
+ 40,mlp.up_proj,0.0000007342,0.05000,1.908
288
+ 40,mlp.down_proj,0.0000000727,0.05000,10.326
289
+ 41,self_attn.k_proj,0.0000000559,0.05000,1.666
290
+ 41,self_attn.v_proj,0.0000000421,0.05000,1.662
291
+ 41,self_attn.q_proj,0.0000002855,0.05000,1.738
292
+ 41,self_attn.o_proj,0.0000000170,0.05000,1.719
293
+ 41,mlp.gate_proj,0.0000008057,0.05000,1.895
294
+ 41,mlp.up_proj,0.0000007766,0.05000,1.907
295
+ 41,mlp.down_proj,0.0000000785,0.05000,10.269
296
+ 42,self_attn.k_proj,0.0000000701,0.05000,1.682
297
+ 42,self_attn.v_proj,0.0000000549,0.05000,1.672
298
+ 42,self_attn.q_proj,0.0000003824,0.05000,1.732
299
+ 42,self_attn.o_proj,0.0000000133,0.05000,1.733
300
+ 42,mlp.gate_proj,0.0000008403,0.05000,1.912
301
+ 42,mlp.up_proj,0.0000008162,0.05000,1.909
302
+ 42,mlp.down_proj,0.0000000892,0.05000,10.328
303
+ 43,self_attn.k_proj,0.0000000691,0.05000,1.662
304
+ 43,self_attn.v_proj,0.0000000489,0.05000,1.658
305
+ 43,self_attn.q_proj,0.0000003654,0.05000,1.719
306
+ 43,self_attn.o_proj,0.0000000184,0.05000,1.724
307
+ 43,mlp.gate_proj,0.0000008706,0.05000,1.906
308
+ 43,mlp.up_proj,0.0000008532,0.05000,1.898
309
+ 43,mlp.down_proj,0.0000000997,0.05000,10.280
310
+ 44,self_attn.k_proj,0.0000000654,0.05000,1.680
311
+ 44,self_attn.v_proj,0.0000000442,0.05000,1.681
312
+ 44,self_attn.q_proj,0.0000003623,0.05000,1.719
313
+ 44,self_attn.o_proj,0.0000000237,0.05000,1.722
314
+ 44,mlp.gate_proj,0.0000008908,0.05000,1.902
315
+ 44,mlp.up_proj,0.0000008894,0.05000,1.899
316
+ 44,mlp.down_proj,0.0000001206,0.05000,10.276
317
+ 45,self_attn.k_proj,0.0000000697,0.05000,1.685
318
+ 45,self_attn.v_proj,0.0000000401,0.05000,1.672
319
+ 45,self_attn.q_proj,0.0000003854,0.05000,1.723
320
+ 45,self_attn.o_proj,0.0000000327,0.05000,1.723
321
+ 45,mlp.gate_proj,0.0000009161,0.05000,1.901
322
+ 45,mlp.up_proj,0.0000009227,0.05000,1.897
323
+ 45,mlp.down_proj,0.0000002357,0.05000,10.295
324
+ 46,self_attn.k_proj,0.0000000762,0.05000,1.683
325
+ 46,self_attn.v_proj,0.0000000453,0.05000,1.669
326
+ 46,self_attn.q_proj,0.0000004139,0.05000,1.718
327
+ 46,self_attn.o_proj,0.0000000476,0.05000,1.726
328
+ 46,mlp.gate_proj,0.0000009351,0.05000,1.919
329
+ 46,mlp.up_proj,0.0000009498,0.05000,1.906
330
+ 46,mlp.down_proj,0.0000001348,0.05000,10.401
331
+ 47,self_attn.k_proj,0.0000000752,0.05000,1.771
332
+ 47,self_attn.v_proj,0.0000000472,0.05000,1.766
333
+ 47,self_attn.q_proj,0.0000004191,0.05000,1.832
334
+ 47,self_attn.o_proj,0.0000000484,0.05000,1.821
335
+ 47,mlp.gate_proj,0.0000009350,0.05000,2.010
336
+ 47,mlp.up_proj,0.0000009616,0.05000,1.989
337
+ 47,mlp.down_proj,0.0000001510,0.05000,10.687
338
+ 48,self_attn.k_proj,0.0000000725,0.05000,1.662
339
+ 48,self_attn.v_proj,0.0000000535,0.05000,1.678
340
+ 48,self_attn.q_proj,0.0000004339,0.05000,1.743
341
+ 48,self_attn.o_proj,0.0000000450,0.05000,1.716
342
+ 48,mlp.gate_proj,0.0000009859,0.05000,1.900
343
+ 48,mlp.up_proj,0.0000010179,0.05000,1.906
344
+ 48,mlp.down_proj,0.0000001680,0.05000,10.308
345
+ 49,self_attn.k_proj,0.0000000722,0.05000,1.781
346
+ 49,self_attn.v_proj,0.0000000513,0.05000,1.760
347
+ 49,self_attn.q_proj,0.0000004106,0.05000,1.806
348
+ 49,self_attn.o_proj,0.0000000500,0.05000,1.833
349
+ 49,mlp.gate_proj,0.0000009837,0.05000,2.007
350
+ 49,mlp.up_proj,0.0000010262,0.05000,2.003
351
+ 49,mlp.down_proj,0.0000001827,0.05000,10.479
352
+ 50,self_attn.k_proj,0.0000000878,0.05000,1.670
353
+ 50,self_attn.v_proj,0.0000000588,0.05000,1.668
354
+ 50,self_attn.q_proj,0.0000005187,0.05000,1.708
355
+ 50,self_attn.o_proj,0.0000000689,0.05000,1.719
356
+ 50,mlp.gate_proj,0.0000009710,0.05000,1.948
357
+ 50,mlp.up_proj,0.0000010223,0.05000,1.898
358
+ 50,mlp.down_proj,0.0000002030,0.05000,10.599
359
+ 51,self_attn.k_proj,0.0000000785,0.05000,1.850
360
+ 51,self_attn.v_proj,0.0000000516,0.05000,1.689
361
+ 51,self_attn.q_proj,0.0000004482,0.05000,1.730
362
+ 51,self_attn.o_proj,0.0000000717,0.05000,1.733
363
+ 51,mlp.gate_proj,0.0000010186,0.05000,1.912
364
+ 51,mlp.up_proj,0.0000010654,0.05000,1.934
365
+ 51,mlp.down_proj,0.0000002185,0.05000,10.323
366
+ 52,self_attn.k_proj,0.0000000687,0.05000,1.682
367
+ 52,self_attn.v_proj,0.0000000637,0.05000,1.651
368
+ 52,self_attn.q_proj,0.0000004243,0.05000,1.713
369
+ 52,self_attn.o_proj,0.0000000786,0.05000,1.719
370
+ 52,mlp.gate_proj,0.0000011731,0.05000,1.947
371
+ 52,mlp.up_proj,0.0000012116,0.05000,1.890
372
+ 52,mlp.down_proj,0.0000002340,0.05000,10.247
373
+ 53,self_attn.k_proj,0.0000000788,0.05000,1.659
374
+ 53,self_attn.v_proj,0.0000000687,0.05000,1.654
375
+ 53,self_attn.q_proj,0.0000004782,0.05000,1.724
376
+ 53,self_attn.o_proj,0.0000000906,0.05000,1.725
377
+ 53,mlp.gate_proj,0.0000012602,0.05000,1.901
378
+ 53,mlp.up_proj,0.0000012900,0.05000,1.897
379
+ 53,mlp.down_proj,0.0000002460,0.05000,10.405
380
+ 54,self_attn.k_proj,0.0000000766,0.05000,2.517
381
+ 54,self_attn.v_proj,0.0000000886,0.05000,1.708
382
+ 54,self_attn.q_proj,0.0000005082,0.05000,1.749
383
+ 54,self_attn.o_proj,0.0000000811,0.05000,1.728
384
+ 54,mlp.gate_proj,0.0000012372,0.05000,2.083
385
+ 54,mlp.up_proj,0.0000012735,0.05000,1.901
386
+ 54,mlp.down_proj,0.0000002715,0.05000,10.699
387
+ 55,self_attn.k_proj,0.0000000740,0.05000,1.671
388
+ 55,self_attn.v_proj,0.0000000864,0.05000,1.672
389
+ 55,self_attn.q_proj,0.0000004974,0.05000,1.727
390
+ 55,self_attn.o_proj,0.0000000965,0.05000,1.724
391
+ 55,mlp.gate_proj,0.0000012793,0.05000,1.915
392
+ 55,mlp.up_proj,0.0000013217,0.05000,1.901
393
+ 55,mlp.down_proj,0.0000003111,0.05000,10.333
394
+ 56,self_attn.k_proj,0.0000000757,0.05000,1.705
395
+ 56,self_attn.v_proj,0.0000000742,0.05000,1.662
396
+ 56,self_attn.q_proj,0.0000004671,0.05000,1.719
397
+ 56,self_attn.o_proj,0.0000001299,0.05000,1.707
398
+ 56,mlp.gate_proj,0.0000014066,0.05000,1.915
399
+ 56,mlp.up_proj,0.0000014399,0.05000,1.896
400
+ 56,mlp.down_proj,0.0000003492,0.05000,10.264
401
+ 57,self_attn.k_proj,0.0000000814,0.05000,1.686
402
+ 57,self_attn.v_proj,0.0000000867,0.05000,1.661
403
+ 57,self_attn.q_proj,0.0000005055,0.05000,1.717
404
+ 57,self_attn.o_proj,0.0000001356,0.05000,1.712
405
+ 57,mlp.gate_proj,0.0000013990,0.05000,1.895
406
+ 57,mlp.up_proj,0.0000014438,0.05000,1.891
407
+ 57,mlp.down_proj,0.0000003847,0.05000,10.443
408
+ 58,self_attn.k_proj,0.0000000745,0.05000,1.664
409
+ 58,self_attn.v_proj,0.0000000881,0.05000,1.659
410
+ 58,self_attn.q_proj,0.0000004971,0.05000,1.703
411
+ 58,self_attn.o_proj,0.0000001591,0.05000,1.705
412
+ 58,mlp.gate_proj,0.0000014434,0.05000,1.901
413
+ 58,mlp.up_proj,0.0000014912,0.05000,1.889
414
+ 58,mlp.down_proj,0.0000004838,0.05000,10.536
415
+ 59,self_attn.k_proj,0.0000000753,0.05000,1.677
416
+ 59,self_attn.v_proj,0.0000000926,0.05000,1.665
417
+ 59,self_attn.q_proj,0.0000004938,0.05000,1.722
418
+ 59,self_attn.o_proj,0.0000001720,0.05000,1.742
419
+ 59,mlp.gate_proj,0.0000015366,0.05000,1.903
420
+ 59,mlp.up_proj,0.0000015528,0.05000,1.898
421
+ 59,mlp.down_proj,0.0000005539,0.05000,10.287
422
+ 60,self_attn.k_proj,0.0000000820,0.05000,1.692
423
+ 60,self_attn.v_proj,0.0000001168,0.05000,1.689
424
+ 60,self_attn.q_proj,0.0000005763,0.05000,1.753
425
+ 60,self_attn.o_proj,0.0000001487,0.05000,1.720
426
+ 60,mlp.gate_proj,0.0000018750,0.05000,1.922
427
+ 60,mlp.up_proj,0.0000018547,0.05000,1.894
428
+ 60,mlp.down_proj,0.0000006279,0.05000,10.338
429
+ 61,self_attn.k_proj,0.0000000843,0.05000,1.682
430
+ 61,self_attn.v_proj,0.0000001284,0.05000,1.673
431
+ 61,self_attn.q_proj,0.0000005832,0.05000,1.728
432
+ 61,self_attn.o_proj,0.0000001704,0.05000,1.719
433
+ 61,mlp.gate_proj,0.0000020632,0.05000,1.944
434
+ 61,mlp.up_proj,0.0000020309,0.05000,1.923
435
+ 61,mlp.down_proj,0.0000007217,0.05000,10.248
436
+ 62,self_attn.k_proj,0.0000000880,0.05000,1.771
437
+ 62,self_attn.v_proj,0.0000001228,0.05000,1.671
438
+ 62,self_attn.q_proj,0.0000006076,0.05000,1.716
439
+ 62,self_attn.o_proj,0.0000001910,0.05000,1.713
440
+ 62,mlp.gate_proj,0.0000024024,0.05000,1.917
441
+ 62,mlp.up_proj,0.0000023178,0.05000,1.895
442
+ 62,mlp.down_proj,0.0000007976,0.05000,10.293
443
+ 63,self_attn.k_proj,0.0000000886,0.05000,1.658
444
+ 63,self_attn.v_proj,0.0000001268,0.05000,1.658
445
+ 63,self_attn.q_proj,0.0000005992,0.05000,1.713
446
+ 63,self_attn.o_proj,0.0000002006,0.05000,1.727
447
+ 63,mlp.gate_proj,0.0000025440,0.05000,1.906
448
+ 63,mlp.up_proj,0.0000024767,0.05000,1.891
449
+ 63,mlp.down_proj,0.0000009258,0.05000,10.266
450
+ 64,self_attn.k_proj,0.0000000947,0.05000,1.699
451
+ 64,self_attn.v_proj,0.0000001271,0.05000,1.666
452
+ 64,self_attn.q_proj,0.0000006335,0.05000,1.731
453
+ 64,self_attn.o_proj,0.0000001935,0.05000,1.729
454
+ 64,mlp.gate_proj,0.0000027792,0.05000,1.926
455
+ 64,mlp.up_proj,0.0000026894,0.05000,1.911
456
+ 64,mlp.down_proj,0.0000010580,0.05000,10.313
457
+ 65,self_attn.k_proj,0.0000000973,0.05000,1.673
458
+ 65,self_attn.v_proj,0.0000001354,0.05000,1.666
459
+ 65,self_attn.q_proj,0.0000006541,0.05000,1.719
460
+ 65,self_attn.o_proj,0.0000002121,0.05000,1.707
461
+ 65,mlp.gate_proj,0.0000030904,0.05000,1.900
462
+ 65,mlp.up_proj,0.0000029994,0.05000,1.912
463
+ 65,mlp.down_proj,0.0000011762,0.05000,10.271
464
+ 66,self_attn.k_proj,0.0000000857,0.05000,1.672
465
+ 66,self_attn.v_proj,0.0000001420,0.05000,1.662
466
+ 66,self_attn.q_proj,0.0000006095,0.05000,1.715
467
+ 66,self_attn.o_proj,0.0000002038,0.05000,1.736
468
+ 66,mlp.gate_proj,0.0000035893,0.05000,1.916
469
+ 66,mlp.up_proj,0.0000034360,0.05000,1.900
470
+ 66,mlp.down_proj,0.0000013113,0.05000,10.293
471
+ 67,self_attn.k_proj,0.0000000931,0.05000,1.689
472
+ 67,self_attn.v_proj,0.0000001635,0.05000,1.655
473
+ 67,self_attn.q_proj,0.0000006569,0.05000,1.704
474
+ 67,self_attn.o_proj,0.0000001514,0.05000,1.716
475
+ 67,mlp.gate_proj,0.0000037963,0.05000,1.903
476
+ 67,mlp.up_proj,0.0000036747,0.05000,1.892
477
+ 67,mlp.down_proj,0.0000014222,0.05000,10.266
478
+ 68,self_attn.k_proj,0.0000000962,0.05000,1.673
479
+ 68,self_attn.v_proj,0.0000001876,0.05000,1.658
480
+ 68,self_attn.q_proj,0.0000006989,0.05000,1.737
481
+ 68,self_attn.o_proj,0.0000001924,0.05000,1.712
482
+ 68,mlp.gate_proj,0.0000040879,0.05000,2.112
483
+ 68,mlp.up_proj,0.0000040017,0.05000,1.889
484
+ 68,mlp.down_proj,0.0000015691,0.05000,10.353
485
+ 69,self_attn.k_proj,0.0000000987,0.05000,1.666
486
+ 69,self_attn.v_proj,0.0000001590,0.05000,1.655
487
+ 69,self_attn.q_proj,0.0000006813,0.05000,1.701
488
+ 69,self_attn.o_proj,0.0000002237,0.05000,1.707
489
+ 69,mlp.gate_proj,0.0000043632,0.05000,1.902
490
+ 69,mlp.up_proj,0.0000043560,0.05000,1.890
491
+ 69,mlp.down_proj,0.0000019097,0.05000,10.358
492
+ 70,self_attn.k_proj,0.0000000952,0.05000,1.686
493
+ 70,self_attn.v_proj,0.0000002180,0.05000,1.663
494
+ 70,self_attn.q_proj,0.0000007084,0.05000,1.715
495
+ 70,self_attn.o_proj,0.0000002977,0.05000,1.720
496
+ 70,mlp.gate_proj,0.0000049191,0.05000,1.918
497
+ 70,mlp.up_proj,0.0000049845,0.05000,1.899
498
+ 70,mlp.down_proj,0.0000023394,0.05000,10.278
499
+ 71,self_attn.k_proj,0.0000001000,0.05000,1.660
500
+ 71,self_attn.v_proj,0.0000002286,0.05000,1.658
501
+ 71,self_attn.q_proj,0.0000007376,0.05000,1.733
502
+ 71,self_attn.o_proj,0.0000003390,0.05000,1.731
503
+ 71,mlp.gate_proj,0.0000053962,0.05000,2.021
504
+ 71,mlp.up_proj,0.0000055504,0.05000,1.898
505
+ 71,mlp.down_proj,0.0000028877,0.05000,10.313
506
+ 72,self_attn.k_proj,0.0000000952,0.05000,1.943
507
+ 72,self_attn.v_proj,0.0000002648,0.05000,1.677
508
+ 72,self_attn.q_proj,0.0000007474,0.05000,1.745
509
+ 72,self_attn.o_proj,0.0000003013,0.05000,1.734
510
+ 72,mlp.gate_proj,0.0000059621,0.05000,1.954
511
+ 72,mlp.up_proj,0.0000062113,0.05000,1.930
512
+ 72,mlp.down_proj,0.0000037827,0.05000,10.344
513
+ 73,self_attn.k_proj,0.0000000986,0.05000,1.670
514
+ 73,self_attn.v_proj,0.0000003097,0.05000,1.668
515
+ 73,self_attn.q_proj,0.0000007756,0.05000,1.735
516
+ 73,self_attn.o_proj,0.0000004082,0.05000,1.731
517
+ 73,mlp.gate_proj,0.0000064299,0.05000,1.938
518
+ 73,mlp.up_proj,0.0000067876,0.05000,1.908
519
+ 73,mlp.down_proj,0.0000047355,0.05000,10.334
520
+ 74,self_attn.k_proj,0.0000001003,0.05000,1.683
521
+ 74,self_attn.v_proj,0.0000002953,0.05000,1.667
522
+ 74,self_attn.q_proj,0.0000008356,0.05000,1.731
523
+ 74,self_attn.o_proj,0.0000004746,0.05000,1.718
524
+ 74,mlp.gate_proj,0.0000067756,0.05000,1.921
525
+ 74,mlp.up_proj,0.0000072664,0.05000,1.912
526
+ 74,mlp.down_proj,0.0000065462,0.05000,10.326
527
+ 75,self_attn.k_proj,0.0000000984,0.05000,1.681
528
+ 75,self_attn.v_proj,0.0000003474,0.05000,1.666
529
+ 75,self_attn.q_proj,0.0000008044,0.05000,1.722
530
+ 75,self_attn.o_proj,0.0000006275,0.05000,1.732
531
+ 75,mlp.gate_proj,0.0000073467,0.05000,1.916
532
+ 75,mlp.up_proj,0.0000079761,0.05000,1.917
533
+ 75,mlp.down_proj,0.0000103067,0.05000,10.338
534
+ 76,self_attn.k_proj,0.0000001002,0.05000,1.991
535
+ 76,self_attn.v_proj,0.0000005677,0.05000,1.683
536
+ 76,self_attn.q_proj,0.0000009104,0.05000,1.728
537
+ 76,self_attn.o_proj,0.0000007738,0.05000,1.726
538
+ 76,mlp.gate_proj,0.0000078915,0.05000,1.928
539
+ 76,mlp.up_proj,0.0000086448,0.05000,1.903
540
+ 76,mlp.down_proj,0.0000162721,0.05000,10.330
541
+ 77,self_attn.k_proj,0.0000000943,0.05000,1.729
542
+ 77,self_attn.v_proj,0.0000003583,0.05000,1.727
543
+ 77,self_attn.q_proj,0.0000008443,0.05000,1.744
544
+ 77,self_attn.o_proj,0.0000011174,0.05000,1.731
545
+ 77,mlp.gate_proj,0.0000083925,0.05000,2.330
546
+ 77,mlp.up_proj,0.0000092032,0.05000,1.905
547
+ 77,mlp.down_proj,0.0000187782,0.05000,10.327
548
+ 78,self_attn.k_proj,0.0000000877,0.05000,1.674
549
+ 78,self_attn.v_proj,0.0000003851,0.05000,1.679
550
+ 78,self_attn.q_proj,0.0000007940,0.05000,1.726
551
+ 78,self_attn.o_proj,0.0000012265,0.05000,1.742
552
+ 78,mlp.gate_proj,0.0000077649,0.05000,1.977
553
+ 78,mlp.up_proj,0.0000083943,0.05000,1.974
554
+ 78,mlp.down_proj,0.0000338986,0.05000,10.428
555
+ 79,self_attn.k_proj,0.0000000757,0.05000,1.670
556
+ 79,self_attn.v_proj,0.0000001361,0.05000,1.666
557
+ 79,self_attn.q_proj,0.0000005678,0.05000,1.748
558
+ 79,self_attn.o_proj,0.0000003669,0.05000,1.729
559
+ 79,mlp.gate_proj,0.0000072500,0.05000,1.921
560
+ 79,mlp.up_proj,0.0000076144,0.05000,1.927
561
+ 79,mlp.down_proj,0.0001956243,0.05000,10.314
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2TokenizerFast",
206
+ "unk_token": null,
207
+ "_commit_hash": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff