Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +134 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +561 -0
- quantize_config.json +24 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- 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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 4,
|
| 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-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d5968bb7a6ce5809cb857b31682106e36df69da6745c10a57c5da03293066d6
|
| 3 |
+
size 3939044856
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8c45f37e7738e7afcf04848f3c51feabb2551a6e977f54f49d511a8c09424dd
|
| 3 |
+
size 3902490424
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0658f2c5f3e989c392641adee14cae37ce0c215b9b120842d0cac44b006d88e3
|
| 3 |
+
size 3981209464
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcba10a30ca1c3040a184436dfe87634b5e150dd0d25b9462363f1e8d3762b5f
|
| 3 |
+
size 3981209464
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d9ed80548ab2af9e9cba02243dfa4782973ccf918be1ac2825d153cc97a49e
|
| 3 |
+
size 3902490648
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c29119a6e44e6faa0deacdc58d1f14120ecb1ab594b646fe0f67b28c93e6f071
|
| 3 |
+
size 3981209464
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed5b1c27aa549ae980c0bc1767ae221e5fca6e6507ab50e5ace5d337fdded8c
|
| 3 |
+
size 3981209464
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49e397e2d96b2121aa3263125c1245726724f9f0180fd40240ce1d41f1896066
|
| 3 |
+
size 3902490648
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23307622fc05f68c5dd8345b82f0b4ba6d8382c563abe3af6ad242750b52b87
|
| 3 |
+
size 3981209464
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684426d08e6af40f0a0b4c468f36c0e1d03de954e65bdfb9752eac80f962d3c5
|
| 3 |
+
size 3446282952
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:293c829ec0dd41d9928275f93d39df98035dccb58c0adc046fbac7a26d72ec83
|
| 3 |
+
size 2491416704
|
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,0.0000000685,0.05000,1.952
|
| 3 |
+
0,self_attn.v_proj,0.0000000051,0.05000,1.721
|
| 4 |
+
0,self_attn.q_proj,0.0000003521,0.05000,1.779
|
| 5 |
+
0,self_attn.o_proj,0.0000000051,0.05000,1.790
|
| 6 |
+
0,mlp.gate_proj,0.0000002079,0.05000,2.237
|
| 7 |
+
0,mlp.up_proj,0.0000001977,0.05000,1.960
|
| 8 |
+
0,mlp.down_proj,0.0000000034,0.05000,10.567
|
| 9 |
+
1,self_attn.k_proj,0.0000000373,0.05000,1.738
|
| 10 |
+
1,self_attn.v_proj,0.0000000025,0.05000,1.740
|
| 11 |
+
1,self_attn.q_proj,0.0000001444,0.05000,1.788
|
| 12 |
+
1,self_attn.o_proj,0.0000000007,0.05000,1.782
|
| 13 |
+
1,mlp.gate_proj,0.0000006684,0.05000,1.988
|
| 14 |
+
1,mlp.up_proj,0.0000006192,0.05000,1.969
|
| 15 |
+
1,mlp.down_proj,0.0002015895,0.05000,10.579
|
| 16 |
+
2,self_attn.k_proj,0.0000020729,0.05000,1.724
|
| 17 |
+
2,self_attn.v_proj,0.0000007911,0.05000,1.714
|
| 18 |
+
2,self_attn.q_proj,0.0000070333,0.05000,1.775
|
| 19 |
+
2,self_attn.o_proj,0.0000000117,0.05000,1.795
|
| 20 |
+
2,mlp.gate_proj,0.0000012298,0.05000,1.968
|
| 21 |
+
2,mlp.up_proj,0.0000011734,0.05000,1.972
|
| 22 |
+
2,mlp.down_proj,0.0000000298,0.05000,10.620
|
| 23 |
+
3,self_attn.k_proj,0.0000015801,0.05000,1.755
|
| 24 |
+
3,self_attn.v_proj,0.0000006056,0.05000,1.764
|
| 25 |
+
3,self_attn.q_proj,0.0000047879,0.05000,1.813
|
| 26 |
+
3,self_attn.o_proj,0.0000000308,0.05000,1.813
|
| 27 |
+
3,mlp.gate_proj,0.0000019761,0.05000,1.979
|
| 28 |
+
3,mlp.up_proj,0.0000019347,0.05000,1.974
|
| 29 |
+
3,mlp.down_proj,0.0000000406,0.05000,10.661
|
| 30 |
+
4,self_attn.k_proj,0.0000022731,0.05000,1.872
|
| 31 |
+
4,self_attn.v_proj,0.0000010830,0.05000,1.864
|
| 32 |
+
4,self_attn.q_proj,0.0000093928,0.05000,1.906
|
| 33 |
+
4,self_attn.o_proj,0.0000000120,0.05000,1.927
|
| 34 |
+
4,mlp.gate_proj,0.0000038092,0.05000,2.084
|
| 35 |
+
4,mlp.up_proj,0.0000037036,0.05000,2.076
|
| 36 |
+
4,mlp.down_proj,0.0000000750,0.05000,10.953
|
| 37 |
+
5,self_attn.k_proj,0.0000031021,0.05000,1.733
|
| 38 |
+
5,self_attn.v_proj,0.0000017217,0.05000,1.725
|
| 39 |
+
5,self_attn.q_proj,0.0000123386,0.05000,1.788
|
| 40 |
+
5,self_attn.o_proj,0.0000000084,0.05000,1.795
|
| 41 |
+
5,mlp.gate_proj,0.0000062782,0.05000,1.972
|
| 42 |
+
5,mlp.up_proj,0.0000060347,0.05000,1.947
|
| 43 |
+
5,mlp.down_proj,0.0000001456,0.05000,10.600
|
| 44 |
+
6,self_attn.k_proj,0.0000020967,0.05000,1.728
|
| 45 |
+
6,self_attn.v_proj,0.0000010817,0.05000,1.713
|
| 46 |
+
6,self_attn.q_proj,0.0000080667,0.05000,1.803
|
| 47 |
+
6,self_attn.o_proj,0.0000000132,0.05000,1.806
|
| 48 |
+
6,mlp.gate_proj,0.0000083323,0.05000,1.982
|
| 49 |
+
6,mlp.up_proj,0.0000080155,0.05000,1.969
|
| 50 |
+
6,mlp.down_proj,0.0000002012,0.05000,10.563
|
| 51 |
+
7,self_attn.k_proj,0.0000029421,0.05000,1.741
|
| 52 |
+
7,self_attn.v_proj,0.0000014289,0.05000,1.724
|
| 53 |
+
7,self_attn.q_proj,0.0000117084,0.05000,1.821
|
| 54 |
+
7,self_attn.o_proj,0.0000000213,0.05000,1.799
|
| 55 |
+
7,mlp.gate_proj,0.0000104807,0.05000,1.985
|
| 56 |
+
7,mlp.up_proj,0.0000101542,0.05000,1.986
|
| 57 |
+
7,mlp.down_proj,0.0000002535,0.05000,10.585
|
| 58 |
+
8,self_attn.k_proj,0.0000027552,0.05000,1.744
|
| 59 |
+
8,self_attn.v_proj,0.0000014088,0.05000,1.738
|
| 60 |
+
8,self_attn.q_proj,0.0000106035,0.05000,1.794
|
| 61 |
+
8,self_attn.o_proj,0.0000000926,0.05000,1.805
|
| 62 |
+
8,mlp.gate_proj,0.0000121578,0.05000,1.984
|
| 63 |
+
8,mlp.up_proj,0.0000115947,0.05000,1.978
|
| 64 |
+
8,mlp.down_proj,0.0000003185,0.05000,10.654
|
| 65 |
+
9,self_attn.k_proj,0.0000073975,0.05000,1.814
|
| 66 |
+
9,self_attn.v_proj,0.0000041334,0.05000,1.730
|
| 67 |
+
9,self_attn.q_proj,0.0000333733,0.05000,1.799
|
| 68 |
+
9,self_attn.o_proj,0.0000001372,0.05000,1.803
|
| 69 |
+
9,mlp.gate_proj,0.0000130155,0.05000,1.955
|
| 70 |
+
9,mlp.up_proj,0.0000125228,0.05000,1.950
|
| 71 |
+
9,mlp.down_proj,0.0000003395,0.05000,10.714
|
| 72 |
+
10,self_attn.k_proj,0.0000043694,0.05000,1.737
|
| 73 |
+
10,self_attn.v_proj,0.0000022361,0.05000,1.723
|
| 74 |
+
10,self_attn.q_proj,0.0000186031,0.05000,1.816
|
| 75 |
+
10,self_attn.o_proj,0.0000001746,0.05000,1.795
|
| 76 |
+
10,mlp.gate_proj,0.0000156931,0.05000,1.980
|
| 77 |
+
10,mlp.up_proj,0.0000150417,0.05000,1.966
|
| 78 |
+
10,mlp.down_proj,0.0000004690,0.05000,10.710
|
| 79 |
+
11,self_attn.k_proj,0.0000051370,0.05000,1.747
|
| 80 |
+
11,self_attn.v_proj,0.0000023946,0.05000,1.736
|
| 81 |
+
11,self_attn.q_proj,0.0000224542,0.05000,1.796
|
| 82 |
+
11,self_attn.o_proj,0.0000001991,0.05000,1.796
|
| 83 |
+
11,mlp.gate_proj,0.0000179378,0.05000,1.990
|
| 84 |
+
11,mlp.up_proj,0.0000170724,0.05000,1.969
|
| 85 |
+
11,mlp.down_proj,0.0000006015,0.05000,10.676
|
| 86 |
+
12,self_attn.k_proj,0.0000068544,0.05000,1.859
|
| 87 |
+
12,self_attn.v_proj,0.0000036612,0.05000,1.839
|
| 88 |
+
12,self_attn.q_proj,0.0000317736,0.05000,1.908
|
| 89 |
+
12,self_attn.o_proj,0.0000003027,0.05000,1.918
|
| 90 |
+
12,mlp.gate_proj,0.0000199806,0.05000,2.102
|
| 91 |
+
12,mlp.up_proj,0.0000191298,0.05000,2.082
|
| 92 |
+
12,mlp.down_proj,0.0000007129,0.05000,11.001
|
| 93 |
+
13,self_attn.k_proj,0.0000063864,0.05000,1.730
|
| 94 |
+
13,self_attn.v_proj,0.0000034330,0.05000,1.719
|
| 95 |
+
13,self_attn.q_proj,0.0000289530,0.05000,1.980
|
| 96 |
+
13,self_attn.o_proj,0.0000002358,0.05000,1.790
|
| 97 |
+
13,mlp.gate_proj,0.0000228015,0.05000,2.018
|
| 98 |
+
13,mlp.up_proj,0.0000218623,0.05000,1.950
|
| 99 |
+
13,mlp.down_proj,0.0000009059,0.05000,10.562
|
| 100 |
+
14,self_attn.k_proj,0.0000061387,0.05000,1.805
|
| 101 |
+
14,self_attn.v_proj,0.0000032689,0.05000,1.739
|
| 102 |
+
14,self_attn.q_proj,0.0000278935,0.05000,2.213
|
| 103 |
+
14,self_attn.o_proj,0.0000004098,0.05000,1.805
|
| 104 |
+
14,mlp.gate_proj,0.0000234183,0.05000,2.002
|
| 105 |
+
14,mlp.up_proj,0.0000224868,0.05000,1.981
|
| 106 |
+
14,mlp.down_proj,0.0000009782,0.05000,10.644
|
| 107 |
+
15,self_attn.k_proj,0.0000076575,0.05000,1.760
|
| 108 |
+
15,self_attn.v_proj,0.0000041983,0.05000,1.746
|
| 109 |
+
15,self_attn.q_proj,0.0000377521,0.05000,1.809
|
| 110 |
+
15,self_attn.o_proj,0.0000003109,0.05000,1.816
|
| 111 |
+
15,mlp.gate_proj,0.0000293268,0.05000,2.150
|
| 112 |
+
15,mlp.up_proj,0.0000280428,0.05000,1.963
|
| 113 |
+
15,mlp.down_proj,0.0000012089,0.05000,10.600
|
| 114 |
+
16,self_attn.k_proj,0.0000071514,0.05000,1.771
|
| 115 |
+
16,self_attn.v_proj,0.0000036904,0.05000,1.765
|
| 116 |
+
16,self_attn.q_proj,0.0000334941,0.05000,1.815
|
| 117 |
+
16,self_attn.o_proj,0.0000003754,0.05000,1.823
|
| 118 |
+
16,mlp.gate_proj,0.0000318242,0.05000,2.024
|
| 119 |
+
16,mlp.up_proj,0.0000304060,0.05000,2.003
|
| 120 |
+
16,mlp.down_proj,0.0000014082,0.05000,10.840
|
| 121 |
+
17,self_attn.k_proj,0.0000058214,0.05000,1.763
|
| 122 |
+
17,self_attn.v_proj,0.0000035011,0.05000,1.745
|
| 123 |
+
17,self_attn.q_proj,0.0000266938,0.05000,1.815
|
| 124 |
+
17,self_attn.o_proj,0.0000004904,0.05000,1.805
|
| 125 |
+
17,mlp.gate_proj,0.0000305605,0.05000,2.189
|
| 126 |
+
17,mlp.up_proj,0.0000294420,0.05000,1.994
|
| 127 |
+
17,mlp.down_proj,0.0000015261,0.05000,10.648
|
| 128 |
+
18,self_attn.k_proj,0.0000113896,0.05000,1.742
|
| 129 |
+
18,self_attn.v_proj,0.0000064052,0.05000,1.727
|
| 130 |
+
18,self_attn.q_proj,0.0000516542,0.05000,1.795
|
| 131 |
+
18,self_attn.o_proj,0.0000004344,0.05000,1.796
|
| 132 |
+
18,mlp.gate_proj,0.0000367808,0.05000,1.973
|
| 133 |
+
18,mlp.up_proj,0.0000351525,0.05000,1.962
|
| 134 |
+
18,mlp.down_proj,0.0000018911,0.05000,10.552
|
| 135 |
+
19,self_attn.k_proj,0.0000147619,0.05000,1.741
|
| 136 |
+
19,self_attn.v_proj,0.0000090224,0.05000,1.746
|
| 137 |
+
19,self_attn.q_proj,0.0000708490,0.05000,1.792
|
| 138 |
+
19,self_attn.o_proj,0.0000004645,0.05000,1.792
|
| 139 |
+
19,mlp.gate_proj,0.0000423705,0.05000,1.967
|
| 140 |
+
19,mlp.up_proj,0.0000406029,0.05000,1.968
|
| 141 |
+
19,mlp.down_proj,0.0000027029,0.05000,10.781
|
| 142 |
+
20,self_attn.k_proj,0.0000055276,0.05000,1.750
|
| 143 |
+
20,self_attn.v_proj,0.0000033355,0.05000,1.743
|
| 144 |
+
20,self_attn.q_proj,0.0000273500,0.05000,1.793
|
| 145 |
+
20,self_attn.o_proj,0.0000006263,0.05000,1.793
|
| 146 |
+
20,mlp.gate_proj,0.0000512864,0.05000,2.252
|
| 147 |
+
20,mlp.up_proj,0.0000486326,0.05000,1.969
|
| 148 |
+
20,mlp.down_proj,0.0000035893,0.05000,10.766
|
| 149 |
+
21,self_attn.k_proj,0.0000045427,0.05000,1.768
|
| 150 |
+
21,self_attn.v_proj,0.0000029989,0.05000,1.780
|
| 151 |
+
21,self_attn.q_proj,0.0000227807,0.05000,1.806
|
| 152 |
+
21,self_attn.o_proj,0.0000011423,0.05000,1.793
|
| 153 |
+
21,mlp.gate_proj,0.0000463502,0.05000,2.002
|
| 154 |
+
21,mlp.up_proj,0.0000443138,0.05000,1.962
|
| 155 |
+
21,mlp.down_proj,0.0000035231,0.05000,10.620
|
| 156 |
+
22,self_attn.k_proj,0.0000118840,0.05000,1.769
|
| 157 |
+
22,self_attn.v_proj,0.0000075208,0.05000,1.737
|
| 158 |
+
22,self_attn.q_proj,0.0000649774,0.05000,1.802
|
| 159 |
+
22,self_attn.o_proj,0.0000013580,0.05000,1.791
|
| 160 |
+
22,mlp.gate_proj,0.0000637017,0.05000,2.294
|
| 161 |
+
22,mlp.up_proj,0.0000610995,0.05000,1.964
|
| 162 |
+
22,mlp.down_proj,0.0000066878,0.05000,10.608
|
| 163 |
+
23,self_attn.k_proj,0.0000096768,0.05000,1.758
|
| 164 |
+
23,self_attn.v_proj,0.0000066151,0.05000,1.746
|
| 165 |
+
23,self_attn.q_proj,0.0000553509,0.05000,1.801
|
| 166 |
+
23,self_attn.o_proj,0.0000017100,0.05000,1.799
|
| 167 |
+
23,mlp.gate_proj,0.0000711954,0.05000,2.026
|
| 168 |
+
23,mlp.up_proj,0.0000675318,0.05000,1.981
|
| 169 |
+
23,mlp.down_proj,0.0000065035,0.05000,10.602
|
| 170 |
+
24,self_attn.k_proj,0.0000083006,0.05000,1.753
|
| 171 |
+
24,self_attn.v_proj,0.0000067867,0.05000,1.741
|
| 172 |
+
24,self_attn.q_proj,0.0000467073,0.05000,1.793
|
| 173 |
+
24,self_attn.o_proj,0.0000016390,0.05000,1.797
|
| 174 |
+
24,mlp.gate_proj,0.0000832089,0.05000,1.972
|
| 175 |
+
24,mlp.up_proj,0.0000782947,0.05000,1.960
|
| 176 |
+
24,mlp.down_proj,0.0000072162,0.05000,10.594
|
| 177 |
+
25,self_attn.k_proj,0.0000148592,0.05000,1.930
|
| 178 |
+
25,self_attn.v_proj,0.0000096430,0.05000,1.742
|
| 179 |
+
25,self_attn.q_proj,0.0000845463,0.05000,1.797
|
| 180 |
+
25,self_attn.o_proj,0.0000019787,0.05000,1.794
|
| 181 |
+
25,mlp.gate_proj,0.0000984830,0.05000,1.975
|
| 182 |
+
25,mlp.up_proj,0.0000933006,0.05000,1.967
|
| 183 |
+
25,mlp.down_proj,0.0000084473,0.05000,10.587
|
| 184 |
+
26,self_attn.k_proj,0.0000107672,0.05000,1.781
|
| 185 |
+
26,self_attn.v_proj,0.0000072195,0.05000,1.763
|
| 186 |
+
26,self_attn.q_proj,0.0000593120,0.05000,1.823
|
| 187 |
+
26,self_attn.o_proj,0.0000023962,0.05000,1.816
|
| 188 |
+
26,mlp.gate_proj,0.0001110225,0.05000,1.998
|
| 189 |
+
26,mlp.up_proj,0.0001054887,0.05000,1.983
|
| 190 |
+
26,mlp.down_proj,0.0000088992,0.05000,10.699
|
| 191 |
+
27,self_attn.k_proj,0.0000106991,0.05000,1.944
|
| 192 |
+
27,self_attn.v_proj,0.0000075662,0.05000,1.731
|
| 193 |
+
27,self_attn.q_proj,0.0000575445,0.05000,1.781
|
| 194 |
+
27,self_attn.o_proj,0.0000020078,0.05000,1.789
|
| 195 |
+
27,mlp.gate_proj,0.0001217312,0.05000,1.969
|
| 196 |
+
27,mlp.up_proj,0.0001160810,0.05000,1.964
|
| 197 |
+
27,mlp.down_proj,0.0000096916,0.05000,10.565
|
| 198 |
+
28,self_attn.k_proj,0.0000104979,0.05000,1.767
|
| 199 |
+
28,self_attn.v_proj,0.0000081629,0.05000,1.760
|
| 200 |
+
28,self_attn.q_proj,0.0000589817,0.05000,1.814
|
| 201 |
+
28,self_attn.o_proj,0.0000016211,0.05000,1.817
|
| 202 |
+
28,mlp.gate_proj,0.0001300697,0.05000,2.004
|
| 203 |
+
28,mlp.up_proj,0.0001248194,0.05000,1.968
|
| 204 |
+
28,mlp.down_proj,0.0000111233,0.05000,10.678
|
| 205 |
+
29,self_attn.k_proj,0.0000137042,0.05000,1.752
|
| 206 |
+
29,self_attn.v_proj,0.0000089406,0.05000,1.733
|
| 207 |
+
29,self_attn.q_proj,0.0000729328,0.05000,1.784
|
| 208 |
+
29,self_attn.o_proj,0.0000026417,0.05000,1.797
|
| 209 |
+
29,mlp.gate_proj,0.0001383661,0.05000,1.988
|
| 210 |
+
29,mlp.up_proj,0.0001325025,0.05000,1.966
|
| 211 |
+
29,mlp.down_proj,0.0000118384,0.05000,11.022
|
| 212 |
+
30,self_attn.k_proj,0.0000135094,0.05000,1.777
|
| 213 |
+
30,self_attn.v_proj,0.0000106211,0.05000,1.751
|
| 214 |
+
30,self_attn.q_proj,0.0000781156,0.05000,1.796
|
| 215 |
+
30,self_attn.o_proj,0.0000030378,0.05000,1.798
|
| 216 |
+
30,mlp.gate_proj,0.0001510154,0.05000,1.980
|
| 217 |
+
30,mlp.up_proj,0.0001430569,0.05000,1.968
|
| 218 |
+
30,mlp.down_proj,0.0000125046,0.05000,10.932
|
| 219 |
+
31,self_attn.k_proj,0.0000150631,0.05000,1.762
|
| 220 |
+
31,self_attn.v_proj,0.0000115141,0.05000,1.744
|
| 221 |
+
31,self_attn.q_proj,0.0000834578,0.05000,1.799
|
| 222 |
+
31,self_attn.o_proj,0.0000020846,0.05000,1.790
|
| 223 |
+
31,mlp.gate_proj,0.0001636284,0.05000,2.262
|
| 224 |
+
31,mlp.up_proj,0.0001546849,0.05000,1.962
|
| 225 |
+
31,mlp.down_proj,0.0000131806,0.05000,10.579
|
| 226 |
+
32,self_attn.k_proj,0.0000166102,0.05000,1.781
|
| 227 |
+
32,self_attn.v_proj,0.0000128024,0.05000,1.740
|
| 228 |
+
32,self_attn.q_proj,0.0000919194,0.05000,1.790
|
| 229 |
+
32,self_attn.o_proj,0.0000023728,0.05000,1.815
|
| 230 |
+
32,mlp.gate_proj,0.0001712901,0.05000,1.978
|
| 231 |
+
32,mlp.up_proj,0.0001622502,0.05000,1.971
|
| 232 |
+
32,mlp.down_proj,0.0000140184,0.05000,10.771
|
| 233 |
+
33,self_attn.k_proj,0.0000155397,0.05000,1.807
|
| 234 |
+
33,self_attn.v_proj,0.0000141580,0.05000,1.770
|
| 235 |
+
33,self_attn.q_proj,0.0000830037,0.05000,1.835
|
| 236 |
+
33,self_attn.o_proj,0.0000017610,0.05000,1.820
|
| 237 |
+
33,mlp.gate_proj,0.0001827080,0.05000,2.015
|
| 238 |
+
33,mlp.up_proj,0.0001707335,0.05000,1.991
|
| 239 |
+
33,mlp.down_proj,0.0000144502,0.05000,10.621
|
| 240 |
+
34,self_attn.k_proj,0.0000175148,0.05000,3.051
|
| 241 |
+
34,self_attn.v_proj,0.0000159380,0.05000,1.756
|
| 242 |
+
34,self_attn.q_proj,0.0000969024,0.05000,1.819
|
| 243 |
+
34,self_attn.o_proj,0.0000012757,0.05000,1.814
|
| 244 |
+
34,mlp.gate_proj,0.0001907635,0.05000,1.991
|
| 245 |
+
34,mlp.up_proj,0.0001778772,0.05000,1.972
|
| 246 |
+
34,mlp.down_proj,0.0000154265,0.05000,10.691
|
| 247 |
+
35,self_attn.k_proj,0.0000191118,0.05000,1.755
|
| 248 |
+
35,self_attn.v_proj,0.0000179529,0.05000,1.751
|
| 249 |
+
35,self_attn.q_proj,0.0001059562,0.05000,1.857
|
| 250 |
+
35,self_attn.o_proj,0.0000010396,0.05000,1.815
|
| 251 |
+
35,mlp.gate_proj,0.0001951154,0.05000,2.000
|
| 252 |
+
35,mlp.up_proj,0.0001831631,0.05000,1.992
|
| 253 |
+
35,mlp.down_proj,0.0000158026,0.05000,10.654
|
| 254 |
+
36,self_attn.k_proj,0.0000201484,0.05000,1.778
|
| 255 |
+
36,self_attn.v_proj,0.0000189599,0.05000,1.774
|
| 256 |
+
36,self_attn.q_proj,0.0001111809,0.05000,1.842
|
| 257 |
+
36,self_attn.o_proj,0.0000018594,0.05000,1.806
|
| 258 |
+
36,mlp.gate_proj,0.0001979247,0.05000,1.987
|
| 259 |
+
36,mlp.up_proj,0.0001868471,0.05000,2.024
|
| 260 |
+
36,mlp.down_proj,0.0000156611,0.05000,10.717
|
| 261 |
+
37,self_attn.k_proj,0.0000191277,0.05000,2.143
|
| 262 |
+
37,self_attn.v_proj,0.0000170317,0.05000,1.762
|
| 263 |
+
37,self_attn.q_proj,0.0001037516,0.05000,1.824
|
| 264 |
+
37,self_attn.o_proj,0.0000016494,0.05000,1.918
|
| 265 |
+
37,mlp.gate_proj,0.0002023499,0.05000,2.012
|
| 266 |
+
37,mlp.up_proj,0.0001926919,0.05000,1.967
|
| 267 |
+
37,mlp.down_proj,0.0000165328,0.05000,10.620
|
| 268 |
+
38,self_attn.k_proj,0.0000190743,0.05000,1.760
|
| 269 |
+
38,self_attn.v_proj,0.0000157472,0.05000,1.751
|
| 270 |
+
38,self_attn.q_proj,0.0001001458,0.05000,1.804
|
| 271 |
+
38,self_attn.o_proj,0.0000027518,0.05000,1.816
|
| 272 |
+
38,mlp.gate_proj,0.0002092387,0.05000,2.005
|
| 273 |
+
38,mlp.up_proj,0.0001991309,0.05000,1.979
|
| 274 |
+
38,mlp.down_proj,0.0000174658,0.05000,10.616
|
| 275 |
+
39,self_attn.k_proj,0.0000183438,0.05000,1.797
|
| 276 |
+
39,self_attn.v_proj,0.0000157707,0.05000,1.786
|
| 277 |
+
39,self_attn.q_proj,0.0000962149,0.05000,1.829
|
| 278 |
+
39,self_attn.o_proj,0.0000025272,0.05000,1.819
|
| 279 |
+
39,mlp.gate_proj,0.0002148854,0.05000,2.003
|
| 280 |
+
39,mlp.up_proj,0.0002056378,0.05000,1.984
|
| 281 |
+
39,mlp.down_proj,0.0000188615,0.05000,10.656
|
| 282 |
+
40,self_attn.k_proj,0.0000182748,0.05000,1.776
|
| 283 |
+
40,self_attn.v_proj,0.0000128602,0.05000,1.801
|
| 284 |
+
40,self_attn.q_proj,0.0000945882,0.05000,1.837
|
| 285 |
+
40,self_attn.o_proj,0.0000040090,0.05000,1.838
|
| 286 |
+
40,mlp.gate_proj,0.0002224625,0.05000,1.998
|
| 287 |
+
40,mlp.up_proj,0.0002146541,0.05000,2.031
|
| 288 |
+
40,mlp.down_proj,0.0000212490,0.05000,10.668
|
| 289 |
+
41,self_attn.k_proj,0.0000163700,0.05000,1.771
|
| 290 |
+
41,self_attn.v_proj,0.0000122546,0.05000,1.760
|
| 291 |
+
41,self_attn.q_proj,0.0000833327,0.05000,1.834
|
| 292 |
+
41,self_attn.o_proj,0.0000048864,0.05000,1.838
|
| 293 |
+
41,mlp.gate_proj,0.0002355262,0.05000,1.998
|
| 294 |
+
41,mlp.up_proj,0.0002269599,0.05000,1.979
|
| 295 |
+
41,mlp.down_proj,0.0000229579,0.05000,10.677
|
| 296 |
+
42,self_attn.k_proj,0.0000204834,0.05000,1.763
|
| 297 |
+
42,self_attn.v_proj,0.0000159663,0.05000,1.760
|
| 298 |
+
42,self_attn.q_proj,0.0001116346,0.05000,1.817
|
| 299 |
+
42,self_attn.o_proj,0.0000038089,0.05000,1.806
|
| 300 |
+
42,mlp.gate_proj,0.0002455023,0.05000,2.074
|
| 301 |
+
42,mlp.up_proj,0.0002384295,0.05000,1.989
|
| 302 |
+
42,mlp.down_proj,0.0000260395,0.05000,10.683
|
| 303 |
+
43,self_attn.k_proj,0.0000201844,0.05000,1.780
|
| 304 |
+
43,self_attn.v_proj,0.0000141727,0.05000,1.764
|
| 305 |
+
43,self_attn.q_proj,0.0001068181,0.05000,1.814
|
| 306 |
+
43,self_attn.o_proj,0.0000052884,0.05000,1.820
|
| 307 |
+
43,mlp.gate_proj,0.0002542797,0.05000,1.992
|
| 308 |
+
43,mlp.up_proj,0.0002492644,0.05000,1.983
|
| 309 |
+
43,mlp.down_proj,0.0000290737,0.05000,10.705
|
| 310 |
+
44,self_attn.k_proj,0.0000191750,0.05000,1.750
|
| 311 |
+
44,self_attn.v_proj,0.0000128655,0.05000,1.774
|
| 312 |
+
44,self_attn.q_proj,0.0001060084,0.05000,1.799
|
| 313 |
+
44,self_attn.o_proj,0.0000067395,0.05000,1.800
|
| 314 |
+
44,mlp.gate_proj,0.0002601013,0.05000,1.982
|
| 315 |
+
44,mlp.up_proj,0.0002597747,0.05000,1.974
|
| 316 |
+
44,mlp.down_proj,0.0000352207,0.05000,10.593
|
| 317 |
+
45,self_attn.k_proj,0.0000203800,0.05000,1.776
|
| 318 |
+
45,self_attn.v_proj,0.0000116344,0.05000,1.754
|
| 319 |
+
45,self_attn.q_proj,0.0001127626,0.05000,1.810
|
| 320 |
+
45,self_attn.o_proj,0.0000093858,0.05000,1.806
|
| 321 |
+
45,mlp.gate_proj,0.0002680701,0.05000,1.988
|
| 322 |
+
45,mlp.up_proj,0.0002698083,0.05000,1.975
|
| 323 |
+
45,mlp.down_proj,0.0000560786,0.05000,10.791
|
| 324 |
+
46,self_attn.k_proj,0.0000223115,0.05000,1.746
|
| 325 |
+
46,self_attn.v_proj,0.0000130194,0.05000,1.736
|
| 326 |
+
46,self_attn.q_proj,0.0001210351,0.05000,1.809
|
| 327 |
+
46,self_attn.o_proj,0.0000144393,0.05000,1.794
|
| 328 |
+
46,mlp.gate_proj,0.0002725730,0.05000,1.981
|
| 329 |
+
46,mlp.up_proj,0.0002767919,0.05000,1.957
|
| 330 |
+
46,mlp.down_proj,0.0000390935,0.05000,10.800
|
| 331 |
+
47,self_attn.k_proj,0.0000220920,0.05000,1.766
|
| 332 |
+
47,self_attn.v_proj,0.0000137250,0.05000,1.765
|
| 333 |
+
47,self_attn.q_proj,0.0001228667,0.05000,2.014
|
| 334 |
+
47,self_attn.o_proj,0.0000139756,0.05000,1.816
|
| 335 |
+
47,mlp.gate_proj,0.0002729540,0.05000,2.008
|
| 336 |
+
47,mlp.up_proj,0.0002807646,0.05000,1.981
|
| 337 |
+
47,mlp.down_proj,0.0000435434,0.05000,10.649
|
| 338 |
+
48,self_attn.k_proj,0.0000213162,0.05000,1.763
|
| 339 |
+
48,self_attn.v_proj,0.0000155181,0.05000,1.758
|
| 340 |
+
48,self_attn.q_proj,0.0001272095,0.05000,1.812
|
| 341 |
+
48,self_attn.o_proj,0.0000127778,0.05000,1.836
|
| 342 |
+
48,mlp.gate_proj,0.0002877861,0.05000,2.007
|
| 343 |
+
48,mlp.up_proj,0.0002972881,0.05000,1.988
|
| 344 |
+
48,mlp.down_proj,0.0000485562,0.05000,10.649
|
| 345 |
+
49,self_attn.k_proj,0.0000211959,0.05000,1.757
|
| 346 |
+
49,self_attn.v_proj,0.0000150000,0.05000,1.748
|
| 347 |
+
49,self_attn.q_proj,0.0001207883,0.05000,1.816
|
| 348 |
+
49,self_attn.o_proj,0.0000144471,0.05000,1.810
|
| 349 |
+
49,mlp.gate_proj,0.0002878208,0.05000,2.077
|
| 350 |
+
49,mlp.up_proj,0.0003003240,0.05000,1.973
|
| 351 |
+
49,mlp.down_proj,0.0000530659,0.05000,10.765
|
| 352 |
+
50,self_attn.k_proj,0.0000258553,0.05000,1.758
|
| 353 |
+
50,self_attn.v_proj,0.0000171321,0.05000,1.749
|
| 354 |
+
50,self_attn.q_proj,0.0001526195,0.05000,1.809
|
| 355 |
+
50,self_attn.o_proj,0.0000200374,0.05000,1.810
|
| 356 |
+
50,mlp.gate_proj,0.0002848091,0.05000,2.031
|
| 357 |
+
50,mlp.up_proj,0.0002997550,0.05000,2.054
|
| 358 |
+
50,mlp.down_proj,0.0000592731,0.05000,10.671
|
| 359 |
+
51,self_attn.k_proj,0.0000231560,0.05000,1.778
|
| 360 |
+
51,self_attn.v_proj,0.0000151993,0.05000,1.752
|
| 361 |
+
51,self_attn.q_proj,0.0001321706,0.05000,1.818
|
| 362 |
+
51,self_attn.o_proj,0.0000205501,0.05000,1.809
|
| 363 |
+
51,mlp.gate_proj,0.0002997619,0.05000,2.003
|
| 364 |
+
51,mlp.up_proj,0.0003137411,0.05000,1.984
|
| 365 |
+
51,mlp.down_proj,0.0000643393,0.05000,11.131
|
| 366 |
+
52,self_attn.k_proj,0.0000203590,0.05000,1.745
|
| 367 |
+
52,self_attn.v_proj,0.0000186799,0.05000,1.742
|
| 368 |
+
52,self_attn.q_proj,0.0001251833,0.05000,1.810
|
| 369 |
+
52,self_attn.o_proj,0.0000231322,0.05000,1.844
|
| 370 |
+
52,mlp.gate_proj,0.0003448580,0.05000,1.992
|
| 371 |
+
52,mlp.up_proj,0.0003562837,0.05000,1.984
|
| 372 |
+
52,mlp.down_proj,0.0000686877,0.05000,11.025
|
| 373 |
+
53,self_attn.k_proj,0.0000233242,0.05000,1.752
|
| 374 |
+
53,self_attn.v_proj,0.0000200947,0.05000,1.762
|
| 375 |
+
53,self_attn.q_proj,0.0001410289,0.05000,1.855
|
| 376 |
+
53,self_attn.o_proj,0.0000270083,0.05000,1.809
|
| 377 |
+
53,mlp.gate_proj,0.0003695233,0.05000,2.113
|
| 378 |
+
53,mlp.up_proj,0.0003783724,0.05000,1.978
|
| 379 |
+
53,mlp.down_proj,0.0000720811,0.05000,10.649
|
| 380 |
+
54,self_attn.k_proj,0.0000225596,0.05000,1.765
|
| 381 |
+
54,self_attn.v_proj,0.0000258560,0.05000,1.752
|
| 382 |
+
54,self_attn.q_proj,0.0001495487,0.05000,2.181
|
| 383 |
+
54,self_attn.o_proj,0.0000239377,0.05000,1.814
|
| 384 |
+
54,mlp.gate_proj,0.0003636169,0.05000,1.974
|
| 385 |
+
54,mlp.up_proj,0.0003744466,0.05000,1.987
|
| 386 |
+
54,mlp.down_proj,0.0000797681,0.05000,10.955
|
| 387 |
+
55,self_attn.k_proj,0.0000218617,0.05000,1.764
|
| 388 |
+
55,self_attn.v_proj,0.0000253199,0.05000,1.758
|
| 389 |
+
55,self_attn.q_proj,0.0001466854,0.05000,1.822
|
| 390 |
+
55,self_attn.o_proj,0.0000282526,0.05000,1.815
|
| 391 |
+
55,mlp.gate_proj,0.0003757199,0.05000,1.990
|
| 392 |
+
55,mlp.up_proj,0.0003881287,0.05000,1.987
|
| 393 |
+
55,mlp.down_proj,0.0000911115,0.05000,10.635
|
| 394 |
+
56,self_attn.k_proj,0.0000223928,0.05000,1.794
|
| 395 |
+
56,self_attn.v_proj,0.0000218095,0.05000,1.772
|
| 396 |
+
56,self_attn.q_proj,0.0001375662,0.05000,1.816
|
| 397 |
+
56,self_attn.o_proj,0.0000379754,0.05000,1.812
|
| 398 |
+
56,mlp.gate_proj,0.0004133328,0.05000,2.341
|
| 399 |
+
56,mlp.up_proj,0.0004231848,0.05000,1.989
|
| 400 |
+
56,mlp.down_proj,0.0001026907,0.05000,10.732
|
| 401 |
+
57,self_attn.k_proj,0.0000240502,0.05000,1.773
|
| 402 |
+
57,self_attn.v_proj,0.0000254070,0.05000,1.769
|
| 403 |
+
57,self_attn.q_proj,0.0001487034,0.05000,1.813
|
| 404 |
+
57,self_attn.o_proj,0.0000396974,0.05000,1.844
|
| 405 |
+
57,mlp.gate_proj,0.0004108658,0.05000,2.431
|
| 406 |
+
57,mlp.up_proj,0.0004240784,0.05000,2.008
|
| 407 |
+
57,mlp.down_proj,0.0001128101,0.05000,10.571
|
| 408 |
+
58,self_attn.k_proj,0.0000219804,0.05000,1.833
|
| 409 |
+
58,self_attn.v_proj,0.0000258982,0.05000,1.745
|
| 410 |
+
58,self_attn.q_proj,0.0001463768,0.05000,1.808
|
| 411 |
+
58,self_attn.o_proj,0.0000463313,0.05000,1.809
|
| 412 |
+
58,mlp.gate_proj,0.0004239820,0.05000,1.996
|
| 413 |
+
58,mlp.up_proj,0.0004381811,0.05000,1.988
|
| 414 |
+
58,mlp.down_proj,0.0001411034,0.05000,10.627
|
| 415 |
+
59,self_attn.k_proj,0.0000221796,0.05000,1.749
|
| 416 |
+
59,self_attn.v_proj,0.0000271249,0.05000,1.760
|
| 417 |
+
59,self_attn.q_proj,0.0001451733,0.05000,1.847
|
| 418 |
+
59,self_attn.o_proj,0.0000497049,0.05000,1.813
|
| 419 |
+
59,mlp.gate_proj,0.0004518706,0.05000,2.006
|
| 420 |
+
59,mlp.up_proj,0.0004566152,0.05000,2.009
|
| 421 |
+
59,mlp.down_proj,0.0001616510,0.05000,10.726
|
| 422 |
+
60,self_attn.k_proj,0.0000241346,0.05000,1.740
|
| 423 |
+
60,self_attn.v_proj,0.0000341904,0.05000,1.735
|
| 424 |
+
60,self_attn.q_proj,0.0001691093,0.05000,1.811
|
| 425 |
+
60,self_attn.o_proj,0.0000432857,0.05000,1.815
|
| 426 |
+
60,mlp.gate_proj,0.0005488024,0.05000,1.983
|
| 427 |
+
60,mlp.up_proj,0.0005428663,0.05000,1.967
|
| 428 |
+
60,mlp.down_proj,0.0001826035,0.05000,10.607
|
| 429 |
+
61,self_attn.k_proj,0.0000247619,0.05000,1.780
|
| 430 |
+
61,self_attn.v_proj,0.0000374423,0.05000,1.778
|
| 431 |
+
61,self_attn.q_proj,0.0001707510,0.05000,1.828
|
| 432 |
+
61,self_attn.o_proj,0.0000489282,0.05000,1.796
|
| 433 |
+
61,mlp.gate_proj,0.0006036149,0.05000,2.043
|
| 434 |
+
61,mlp.up_proj,0.0005943566,0.05000,1.986
|
| 435 |
+
61,mlp.down_proj,0.0002096645,0.05000,10.626
|
| 436 |
+
62,self_attn.k_proj,0.0000260108,0.05000,1.744
|
| 437 |
+
62,self_attn.v_proj,0.0000357173,0.05000,1.747
|
| 438 |
+
62,self_attn.q_proj,0.0001779701,0.05000,1.806
|
| 439 |
+
62,self_attn.o_proj,0.0000560566,0.05000,1.800
|
| 440 |
+
62,mlp.gate_proj,0.0007026849,0.05000,1.983
|
| 441 |
+
62,mlp.up_proj,0.0006780243,0.05000,1.958
|
| 442 |
+
62,mlp.down_proj,0.0002315546,0.05000,10.636
|
| 443 |
+
63,self_attn.k_proj,0.0000259721,0.05000,1.775
|
| 444 |
+
63,self_attn.v_proj,0.0000370121,0.05000,1.768
|
| 445 |
+
63,self_attn.q_proj,0.0001751592,0.05000,1.833
|
| 446 |
+
63,self_attn.o_proj,0.0000582709,0.05000,1.794
|
| 447 |
+
63,mlp.gate_proj,0.0007427418,0.05000,2.061
|
| 448 |
+
63,mlp.up_proj,0.0007230977,0.05000,1.987
|
| 449 |
+
63,mlp.down_proj,0.0002685315,0.05000,10.627
|
| 450 |
+
64,self_attn.k_proj,0.0000277544,0.05000,1.773
|
| 451 |
+
64,self_attn.v_proj,0.0000370765,0.05000,1.817
|
| 452 |
+
64,self_attn.q_proj,0.0001851113,0.05000,1.824
|
| 453 |
+
64,self_attn.o_proj,0.0000561820,0.05000,1.813
|
| 454 |
+
64,mlp.gate_proj,0.0008117926,0.05000,1.997
|
| 455 |
+
64,mlp.up_proj,0.0007852368,0.05000,1.984
|
| 456 |
+
64,mlp.down_proj,0.0003075914,0.05000,10.902
|
| 457 |
+
65,self_attn.k_proj,0.0000285461,0.05000,1.787
|
| 458 |
+
65,self_attn.v_proj,0.0000393212,0.05000,1.763
|
| 459 |
+
65,self_attn.q_proj,0.0001911329,0.05000,1.814
|
| 460 |
+
65,self_attn.o_proj,0.0000612525,0.05000,1.806
|
| 461 |
+
65,mlp.gate_proj,0.0009011056,0.05000,1.996
|
| 462 |
+
65,mlp.up_proj,0.0008748247,0.05000,1.984
|
| 463 |
+
65,mlp.down_proj,0.0003410627,0.05000,10.640
|
| 464 |
+
66,self_attn.k_proj,0.0000250020,0.05000,1.769
|
| 465 |
+
66,self_attn.v_proj,0.0000412053,0.05000,1.804
|
| 466 |
+
66,self_attn.q_proj,0.0001777558,0.05000,1.822
|
| 467 |
+
66,self_attn.o_proj,0.0000593562,0.05000,1.806
|
| 468 |
+
66,mlp.gate_proj,0.0010464112,0.05000,1.991
|
| 469 |
+
66,mlp.up_proj,0.0010015315,0.05000,1.975
|
| 470 |
+
66,mlp.down_proj,0.0003793334,0.05000,10.629
|
| 471 |
+
67,self_attn.k_proj,0.0000271901,0.05000,1.769
|
| 472 |
+
67,self_attn.v_proj,0.0000476565,0.05000,1.783
|
| 473 |
+
67,self_attn.q_proj,0.0001915081,0.05000,1.825
|
| 474 |
+
67,self_attn.o_proj,0.0000432816,0.05000,1.820
|
| 475 |
+
67,mlp.gate_proj,0.0011060469,0.05000,2.151
|
| 476 |
+
67,mlp.up_proj,0.0010709054,0.05000,1.993
|
| 477 |
+
67,mlp.down_proj,0.0004122393,0.05000,10.675
|
| 478 |
+
68,self_attn.k_proj,0.0000280968,0.05000,1.749
|
| 479 |
+
68,self_attn.v_proj,0.0000545287,0.05000,1.744
|
| 480 |
+
68,self_attn.q_proj,0.0002037208,0.05000,1.818
|
| 481 |
+
68,self_attn.o_proj,0.0000551032,0.05000,1.805
|
| 482 |
+
68,mlp.gate_proj,0.0011910696,0.05000,2.007
|
| 483 |
+
68,mlp.up_proj,0.0011660263,0.05000,2.002
|
| 484 |
+
68,mlp.down_proj,0.0004548276,0.05000,10.648
|
| 485 |
+
69,self_attn.k_proj,0.0000288387,0.05000,1.752
|
| 486 |
+
69,self_attn.v_proj,0.0000463445,0.05000,1.772
|
| 487 |
+
69,self_attn.q_proj,0.0001985468,0.05000,1.822
|
| 488 |
+
69,self_attn.o_proj,0.0000651683,0.05000,1.812
|
| 489 |
+
69,mlp.gate_proj,0.0012707321,0.05000,2.017
|
| 490 |
+
69,mlp.up_proj,0.0012687438,0.05000,1.987
|
| 491 |
+
69,mlp.down_proj,0.0005535664,0.05000,10.638
|
| 492 |
+
70,self_attn.k_proj,0.0000278806,0.05000,1.833
|
| 493 |
+
70,self_attn.v_proj,0.0000634856,0.05000,1.766
|
| 494 |
+
70,self_attn.q_proj,0.0002063552,0.05000,1.824
|
| 495 |
+
70,self_attn.o_proj,0.0000850229,0.05000,1.822
|
| 496 |
+
70,mlp.gate_proj,0.0014331741,0.05000,2.091
|
| 497 |
+
70,mlp.up_proj,0.0014520215,0.05000,1.987
|
| 498 |
+
70,mlp.down_proj,0.0006782743,0.05000,10.642
|
| 499 |
+
71,self_attn.k_proj,0.0000291759,0.05000,1.771
|
| 500 |
+
71,self_attn.v_proj,0.0000665733,0.05000,1.748
|
| 501 |
+
71,self_attn.q_proj,0.0002151191,0.05000,1.818
|
| 502 |
+
71,self_attn.o_proj,0.0000977527,0.05000,1.800
|
| 503 |
+
71,mlp.gate_proj,0.0015705100,0.05000,2.357
|
| 504 |
+
71,mlp.up_proj,0.0016157514,0.05000,1.970
|
| 505 |
+
71,mlp.down_proj,0.0008346530,0.05000,10.610
|
| 506 |
+
72,self_attn.k_proj,0.0000277748,0.05000,1.781
|
| 507 |
+
72,self_attn.v_proj,0.0000769196,0.05000,1.770
|
| 508 |
+
72,self_attn.q_proj,0.0002174281,0.05000,1.811
|
| 509 |
+
72,self_attn.o_proj,0.0000868489,0.05000,1.822
|
| 510 |
+
72,mlp.gate_proj,0.0017338871,0.05000,2.008
|
| 511 |
+
72,mlp.up_proj,0.0018062971,0.05000,2.012
|
| 512 |
+
72,mlp.down_proj,0.0010927289,0.05000,10.713
|
| 513 |
+
73,self_attn.k_proj,0.0000286837,0.05000,1.855
|
| 514 |
+
73,self_attn.v_proj,0.0000898291,0.05000,1.765
|
| 515 |
+
73,self_attn.q_proj,0.0002256701,0.05000,1.823
|
| 516 |
+
73,self_attn.o_proj,0.0001178069,0.05000,1.812
|
| 517 |
+
73,mlp.gate_proj,0.0018677687,0.05000,2.000
|
| 518 |
+
73,mlp.up_proj,0.0019719667,0.05000,1.974
|
| 519 |
+
73,mlp.down_proj,0.0013667705,0.05000,10.622
|
| 520 |
+
74,self_attn.k_proj,0.0000291870,0.05000,1.782
|
| 521 |
+
74,self_attn.v_proj,0.0000854093,0.05000,1.765
|
| 522 |
+
74,self_attn.q_proj,0.0002426886,0.05000,1.822
|
| 523 |
+
74,self_attn.o_proj,0.0001362484,0.05000,1.820
|
| 524 |
+
74,mlp.gate_proj,0.0019655873,0.05000,1.998
|
| 525 |
+
74,mlp.up_proj,0.0021086635,0.05000,1.984
|
| 526 |
+
74,mlp.down_proj,0.0018890411,0.05000,10.693
|
| 527 |
+
75,self_attn.k_proj,0.0000286997,0.05000,1.761
|
| 528 |
+
75,self_attn.v_proj,0.0001000469,0.05000,1.738
|
| 529 |
+
75,self_attn.q_proj,0.0002336207,0.05000,1.786
|
| 530 |
+
75,self_attn.o_proj,0.0001834656,0.05000,1.802
|
| 531 |
+
75,mlp.gate_proj,0.0021311569,0.05000,1.993
|
| 532 |
+
75,mlp.up_proj,0.0023135146,0.05000,2.004
|
| 533 |
+
75,mlp.down_proj,0.0029731325,0.05000,10.627
|
| 534 |
+
76,self_attn.k_proj,0.0000291649,0.05000,1.759
|
| 535 |
+
76,self_attn.v_proj,0.0001630616,0.05000,1.747
|
| 536 |
+
76,self_attn.q_proj,0.0002645282,0.05000,1.796
|
| 537 |
+
76,self_attn.o_proj,0.0002224826,0.05000,1.891
|
| 538 |
+
76,mlp.gate_proj,0.0022946957,0.05000,2.193
|
| 539 |
+
76,mlp.up_proj,0.0025133457,0.05000,1.982
|
| 540 |
+
76,mlp.down_proj,0.0047117417,0.05000,10.648
|
| 541 |
+
77,self_attn.k_proj,0.0000274915,0.05000,1.782
|
| 542 |
+
77,self_attn.v_proj,0.0001038129,0.05000,1.765
|
| 543 |
+
77,self_attn.q_proj,0.0002454595,0.05000,1.843
|
| 544 |
+
77,self_attn.o_proj,0.0003246888,0.05000,1.824
|
| 545 |
+
77,mlp.gate_proj,0.0024383952,0.05000,2.030
|
| 546 |
+
77,mlp.up_proj,0.0026753585,0.05000,1.995
|
| 547 |
+
77,mlp.down_proj,0.0054391157,0.05000,10.677
|
| 548 |
+
78,self_attn.k_proj,0.0000255497,0.05000,1.753
|
| 549 |
+
78,self_attn.v_proj,0.0001116223,0.05000,1.773
|
| 550 |
+
78,self_attn.q_proj,0.0002304750,0.05000,1.823
|
| 551 |
+
78,self_attn.o_proj,0.0003565016,0.05000,1.820
|
| 552 |
+
78,mlp.gate_proj,0.0022525496,0.05000,1.985
|
| 553 |
+
78,mlp.up_proj,0.0024347074,0.05000,1.993
|
| 554 |
+
78,mlp.down_proj,0.0097805633,0.05000,10.660
|
| 555 |
+
79,self_attn.k_proj,0.0000219384,0.05000,1.772
|
| 556 |
+
79,self_attn.v_proj,0.0000395143,0.05000,1.750
|
| 557 |
+
79,self_attn.q_proj,0.0001646463,0.05000,1.812
|
| 558 |
+
79,self_attn.o_proj,0.0001054719,0.05000,1.787
|
| 559 |
+
79,mlp.gate_proj,0.0021020814,0.05000,2.001
|
| 560 |
+
79,mlp.up_proj,0.0022070014,0.05000,2.006
|
| 561 |
+
79,mlp.down_proj,0.0153322140,0.05000,10.670
|
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 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
|
|
|