Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +169 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +37 -0
- quant_log.csv +253 -0
- quantize_config.json +24 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- video_preprocessor_config.json +43 -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 MiMo, an AI assistant developed by Xiaomi.' }}
|
| 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 MiMo, an AI assistant developed by Xiaomi.<|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 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 32,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bits": 4,
|
| 22 |
+
"checkpoint_format": "gptq",
|
| 23 |
+
"desc_act": true,
|
| 24 |
+
"group_size": 128,
|
| 25 |
+
"hyb_act": false,
|
| 26 |
+
"lm_head": false,
|
| 27 |
+
"meta": {
|
| 28 |
+
"damp_auto_increment": 0.01,
|
| 29 |
+
"damp_percent": 0.05,
|
| 30 |
+
"mse": 0.0,
|
| 31 |
+
"quantizer": [
|
| 32 |
+
"gptqmodel:4.0.0-dev"
|
| 33 |
+
],
|
| 34 |
+
"static_groups": false,
|
| 35 |
+
"true_sequential": true,
|
| 36 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 37 |
+
"v2": false,
|
| 38 |
+
"v2_alpha": 0.25
|
| 39 |
+
},
|
| 40 |
+
"pack_dtype": "int32",
|
| 41 |
+
"quant_method": "gptq",
|
| 42 |
+
"sym": true
|
| 43 |
+
},
|
| 44 |
+
"rms_norm_eps": 1e-05,
|
| 45 |
+
"rope_scaling": {
|
| 46 |
+
"mrope_section": [
|
| 47 |
+
16,
|
| 48 |
+
24,
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"rope_type": "default",
|
| 52 |
+
"type": "default"
|
| 53 |
+
},
|
| 54 |
+
"rope_theta": 640000.0,
|
| 55 |
+
"sliding_window": 8192,
|
| 56 |
+
"text_config": {
|
| 57 |
+
"architectures": [
|
| 58 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 59 |
+
],
|
| 60 |
+
"attention_bias": true,
|
| 61 |
+
"attention_dropout": 0.0,
|
| 62 |
+
"bos_token_id": 151643,
|
| 63 |
+
"eos_token_id": 151645,
|
| 64 |
+
"hidden_act": "silu",
|
| 65 |
+
"hidden_size": 4096,
|
| 66 |
+
"image_token_id": null,
|
| 67 |
+
"initializer_range": 0.02,
|
| 68 |
+
"intermediate_size": 11008,
|
| 69 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 95 |
+
"full_attention",
|
| 96 |
+
"full_attention",
|
| 97 |
+
"full_attention",
|
| 98 |
+
"full_attention",
|
| 99 |
+
"full_attention",
|
| 100 |
+
"full_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"full_attention",
|
| 103 |
+
"full_attention",
|
| 104 |
+
"full_attention",
|
| 105 |
+
"full_attention"
|
| 106 |
+
],
|
| 107 |
+
"max_position_embeddings": 128000,
|
| 108 |
+
"max_window_layers": 32,
|
| 109 |
+
"model_type": "qwen2_5_vl_text",
|
| 110 |
+
"num_attention_heads": 32,
|
| 111 |
+
"num_hidden_layers": 36,
|
| 112 |
+
"num_key_value_heads": 8,
|
| 113 |
+
"rms_norm_eps": 1e-05,
|
| 114 |
+
"rope_scaling": {
|
| 115 |
+
"mrope_section": [
|
| 116 |
+
16,
|
| 117 |
+
24,
|
| 118 |
+
24
|
| 119 |
+
],
|
| 120 |
+
"rope_type": "default",
|
| 121 |
+
"type": "default"
|
| 122 |
+
},
|
| 123 |
+
"rope_theta": 640000.0,
|
| 124 |
+
"sliding_window": null,
|
| 125 |
+
"torch_dtype": "bfloat16",
|
| 126 |
+
"use_cache": true,
|
| 127 |
+
"use_sliding_window": false,
|
| 128 |
+
"video_token_id": null,
|
| 129 |
+
"vision_end_token_id": 151653,
|
| 130 |
+
"vision_start_token_id": 151652,
|
| 131 |
+
"vision_token_id": 151654,
|
| 132 |
+
"vocab_size": 151680
|
| 133 |
+
},
|
| 134 |
+
"tie_word_embeddings": false,
|
| 135 |
+
"torch_dtype": "bfloat16",
|
| 136 |
+
"transformers_version": "4.55.2",
|
| 137 |
+
"use_cache": true,
|
| 138 |
+
"use_sliding_window": false,
|
| 139 |
+
"video_token_id": 151656,
|
| 140 |
+
"vision_config": {
|
| 141 |
+
"depth": 32,
|
| 142 |
+
"fullatt_block_indexes": [
|
| 143 |
+
7,
|
| 144 |
+
15,
|
| 145 |
+
23,
|
| 146 |
+
31
|
| 147 |
+
],
|
| 148 |
+
"hidden_act": "silu",
|
| 149 |
+
"hidden_size": 1280,
|
| 150 |
+
"in_channels": 3,
|
| 151 |
+
"in_chans": 3,
|
| 152 |
+
"initializer_range": 0.02,
|
| 153 |
+
"intermediate_size": 3456,
|
| 154 |
+
"model_type": "qwen2_5_vl",
|
| 155 |
+
"num_heads": 16,
|
| 156 |
+
"out_hidden_size": 4096,
|
| 157 |
+
"patch_size": 14,
|
| 158 |
+
"spatial_merge_size": 2,
|
| 159 |
+
"spatial_patch_size": 14,
|
| 160 |
+
"temporal_patch_size": 2,
|
| 161 |
+
"tokens_per_second": 2,
|
| 162 |
+
"torch_dtype": "bfloat16",
|
| 163 |
+
"window_size": 112
|
| 164 |
+
},
|
| 165 |
+
"vision_end_token_id": 151653,
|
| 166 |
+
"vision_start_token_id": 151652,
|
| 167 |
+
"vision_token_id": 151654,
|
| 168 |
+
"vocab_size": 151680
|
| 169 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151643,
|
| 5 |
+
151645
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.55.2"
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9215e5d484d511531f9334f03f743d10cac9a10fecc2c845f963b790833226e
|
| 3 |
+
size 3993418072
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b8808d8ac40e0f4d8cc8ece7ee0817182cb54e59a52a47ea2842088bb64ef13
|
| 3 |
+
size 3179631912
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_rescale": true,
|
| 11 |
+
"do_resize": true,
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.48145466,
|
| 14 |
+
0.4578275,
|
| 15 |
+
0.40821073
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.26862954,
|
| 20 |
+
0.26130258,
|
| 21 |
+
0.27577711
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_pixels": 12845056,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_pixels": 3136,
|
| 27 |
+
"patch_size": 14,
|
| 28 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 29 |
+
"resample": 3,
|
| 30 |
+
"rescale_factor": 0.00392156862745098,
|
| 31 |
+
"return_tensors": null,
|
| 32 |
+
"size": {
|
| 33 |
+
"longest_edge": 12845056,
|
| 34 |
+
"shortest_edge": 3136
|
| 35 |
+
},
|
| 36 |
+
"temporal_patch_size": 2
|
| 37 |
+
}
|
quant_log.csv
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.0000048419,0.05000,0.850
|
| 3 |
+
0,self_attn.v_proj,0.0000002997,0.05000,0.630
|
| 4 |
+
0,self_attn.q_proj,0.0000167354,0.05000,0.626
|
| 5 |
+
0,self_attn.o_proj,0.0000000223,0.05000,0.637
|
| 6 |
+
0,mlp.up_proj,0.0000032546,0.05000,0.637
|
| 7 |
+
0,mlp.gate_proj,0.0000036725,0.05000,0.630
|
| 8 |
+
0,mlp.down_proj,0.0000000411,0.05000,1.828
|
| 9 |
+
1,self_attn.k_proj,0.0000076643,0.05000,0.627
|
| 10 |
+
1,self_attn.v_proj,0.0000003606,0.05000,0.624
|
| 11 |
+
1,self_attn.q_proj,0.0000321719,0.05000,0.616
|
| 12 |
+
1,self_attn.o_proj,0.0000000056,0.05000,0.618
|
| 13 |
+
1,mlp.up_proj,0.0000095029,0.05000,0.628
|
| 14 |
+
1,mlp.gate_proj,0.0000114402,0.05000,0.619
|
| 15 |
+
1,mlp.down_proj,0.0000001836,0.05000,1.810
|
| 16 |
+
2,self_attn.k_proj,0.0000043770,0.05000,0.624
|
| 17 |
+
2,self_attn.v_proj,0.0000003038,0.05000,0.627
|
| 18 |
+
2,self_attn.q_proj,0.0000100549,0.05000,0.625
|
| 19 |
+
2,self_attn.o_proj,0.0000000621,0.05000,0.623
|
| 20 |
+
2,mlp.up_proj,0.0000180997,0.05000,0.633
|
| 21 |
+
2,mlp.gate_proj,0.0000231815,0.05000,0.625
|
| 22 |
+
2,mlp.down_proj,0.0002654786,0.05000,1.819
|
| 23 |
+
3,self_attn.k_proj,0.0000244940,0.05000,0.705
|
| 24 |
+
3,self_attn.v_proj,0.0000029089,0.05000,0.709
|
| 25 |
+
3,self_attn.q_proj,0.0000569491,0.05000,0.788
|
| 26 |
+
3,self_attn.o_proj,0.0000001189,0.05000,1.145
|
| 27 |
+
3,mlp.up_proj,0.0000309714,0.05000,0.992
|
| 28 |
+
3,mlp.gate_proj,0.0000393766,0.05000,0.805
|
| 29 |
+
3,mlp.down_proj,0.0000008132,0.05000,2.261
|
| 30 |
+
4,self_attn.k_proj,0.0000185136,0.05000,0.653
|
| 31 |
+
4,self_attn.v_proj,0.0000038799,0.05000,0.648
|
| 32 |
+
4,self_attn.q_proj,0.0000470942,0.05000,0.650
|
| 33 |
+
4,self_attn.o_proj,0.0000001687,0.05000,0.653
|
| 34 |
+
4,mlp.up_proj,0.0000415087,0.05000,0.654
|
| 35 |
+
4,mlp.gate_proj,0.0000543395,0.05000,0.649
|
| 36 |
+
4,mlp.down_proj,0.0000013035,0.05000,1.883
|
| 37 |
+
5,self_attn.k_proj,0.0000276466,0.05000,0.652
|
| 38 |
+
5,self_attn.v_proj,0.0000060560,0.05000,0.645
|
| 39 |
+
5,self_attn.q_proj,0.0000736839,0.05000,0.651
|
| 40 |
+
5,self_attn.o_proj,0.0000002573,0.05000,0.647
|
| 41 |
+
5,mlp.up_proj,0.0000517369,0.05000,0.657
|
| 42 |
+
5,mlp.gate_proj,0.0000695619,0.05000,0.651
|
| 43 |
+
5,mlp.down_proj,0.0000017211,0.05000,1.878
|
| 44 |
+
6,self_attn.k_proj,0.0000330041,0.05000,0.651
|
| 45 |
+
6,self_attn.v_proj,0.0000069070,0.05000,0.651
|
| 46 |
+
6,self_attn.q_proj,0.0000812897,0.05000,0.643
|
| 47 |
+
6,self_attn.o_proj,0.0000003508,0.05000,0.647
|
| 48 |
+
6,mlp.up_proj,0.0000635668,0.05000,0.659
|
| 49 |
+
6,mlp.gate_proj,0.0000851637,0.05000,0.646
|
| 50 |
+
6,mlp.down_proj,0.0000023039,0.05000,1.879
|
| 51 |
+
7,self_attn.k_proj,0.0000385079,0.05000,0.647
|
| 52 |
+
7,self_attn.v_proj,0.0000074747,0.05000,0.639
|
| 53 |
+
7,self_attn.q_proj,0.0000916270,0.05000,0.645
|
| 54 |
+
7,self_attn.o_proj,0.0000004776,0.05000,0.649
|
| 55 |
+
7,mlp.up_proj,0.0000753082,0.05000,0.632
|
| 56 |
+
7,mlp.gate_proj,0.0000999293,0.05000,0.630
|
| 57 |
+
7,mlp.down_proj,0.0000029323,0.05000,1.815
|
| 58 |
+
8,self_attn.k_proj,0.0000367004,0.05000,0.626
|
| 59 |
+
8,self_attn.v_proj,0.0000073900,0.05000,0.623
|
| 60 |
+
8,self_attn.q_proj,0.0000872228,0.05000,0.625
|
| 61 |
+
8,self_attn.o_proj,0.0000006690,0.05000,0.627
|
| 62 |
+
8,mlp.up_proj,0.0000885129,0.05000,0.636
|
| 63 |
+
8,mlp.gate_proj,0.0001128771,0.05000,0.628
|
| 64 |
+
8,mlp.down_proj,0.0000036657,0.05000,1.816
|
| 65 |
+
9,self_attn.k_proj,0.0000284881,0.05000,0.638
|
| 66 |
+
9,self_attn.v_proj,0.0000077017,0.05000,0.637
|
| 67 |
+
9,self_attn.q_proj,0.0000759375,0.05000,0.628
|
| 68 |
+
9,self_attn.o_proj,0.0000012961,0.05000,0.631
|
| 69 |
+
9,mlp.up_proj,0.0001003286,0.05000,0.638
|
| 70 |
+
9,mlp.gate_proj,0.0001320431,0.05000,0.639
|
| 71 |
+
9,mlp.down_proj,0.0000046516,0.05000,1.860
|
| 72 |
+
10,self_attn.k_proj,0.0000381674,0.05000,0.634
|
| 73 |
+
10,self_attn.v_proj,0.0000107823,0.05000,0.631
|
| 74 |
+
10,self_attn.q_proj,0.0001037492,0.05000,0.644
|
| 75 |
+
10,self_attn.o_proj,0.0000010537,0.05000,0.633
|
| 76 |
+
10,mlp.up_proj,0.0001127919,0.05000,0.638
|
| 77 |
+
10,mlp.gate_proj,0.0001479486,0.05000,0.631
|
| 78 |
+
10,mlp.down_proj,0.0000056188,0.05000,1.825
|
| 79 |
+
11,self_attn.k_proj,0.0000302041,0.05000,0.633
|
| 80 |
+
11,self_attn.v_proj,0.0000086588,0.05000,0.626
|
| 81 |
+
11,self_attn.q_proj,0.0000839409,0.05000,0.659
|
| 82 |
+
11,self_attn.o_proj,0.0000021412,0.05000,0.640
|
| 83 |
+
11,mlp.up_proj,0.0001184465,0.05000,0.642
|
| 84 |
+
11,mlp.gate_proj,0.0001567948,0.05000,0.636
|
| 85 |
+
11,mlp.down_proj,0.0000067630,0.05000,1.895
|
| 86 |
+
12,self_attn.k_proj,0.0000381159,0.05000,0.629
|
| 87 |
+
12,self_attn.v_proj,0.0000090701,0.05000,0.624
|
| 88 |
+
12,self_attn.q_proj,0.0000963664,0.05000,0.631
|
| 89 |
+
12,self_attn.o_proj,0.0000025287,0.05000,0.625
|
| 90 |
+
12,mlp.up_proj,0.0001218755,0.05000,0.644
|
| 91 |
+
12,mlp.gate_proj,0.0001644475,0.05000,0.631
|
| 92 |
+
12,mlp.down_proj,0.0000067528,0.05000,1.815
|
| 93 |
+
13,self_attn.k_proj,0.0000369779,0.05000,0.624
|
| 94 |
+
13,self_attn.v_proj,0.0000091756,0.05000,0.620
|
| 95 |
+
13,self_attn.q_proj,0.0000920428,0.05000,0.626
|
| 96 |
+
13,self_attn.o_proj,0.0000024624,0.05000,0.637
|
| 97 |
+
13,mlp.up_proj,0.0001204836,0.05000,0.638
|
| 98 |
+
13,mlp.gate_proj,0.0001520465,0.05000,0.650
|
| 99 |
+
13,mlp.down_proj,0.0000066967,0.05000,1.892
|
| 100 |
+
14,self_attn.k_proj,0.0000440962,0.05000,0.625
|
| 101 |
+
14,self_attn.v_proj,0.0000113788,0.05000,0.623
|
| 102 |
+
14,self_attn.q_proj,0.0001158475,0.05000,0.630
|
| 103 |
+
14,self_attn.o_proj,0.0000018829,0.05000,0.645
|
| 104 |
+
14,mlp.up_proj,0.0001208100,0.05000,0.642
|
| 105 |
+
14,mlp.gate_proj,0.0001354142,0.05000,0.635
|
| 106 |
+
14,mlp.down_proj,0.0000068718,0.05000,1.955
|
| 107 |
+
15,self_attn.k_proj,0.0000359595,0.05000,0.693
|
| 108 |
+
15,self_attn.v_proj,0.0000102523,0.05000,0.691
|
| 109 |
+
15,self_attn.q_proj,0.0000921235,0.05000,0.707
|
| 110 |
+
15,self_attn.o_proj,0.0000030046,0.05000,0.697
|
| 111 |
+
15,mlp.up_proj,0.0001190225,0.05000,0.692
|
| 112 |
+
15,mlp.gate_proj,0.0001351498,0.05000,0.696
|
| 113 |
+
15,mlp.down_proj,0.0000065856,0.05000,2.007
|
| 114 |
+
16,self_attn.k_proj,0.0000468016,0.05000,0.627
|
| 115 |
+
16,self_attn.v_proj,0.0000091339,0.05000,0.625
|
| 116 |
+
16,self_attn.q_proj,0.0001079922,0.05000,0.641
|
| 117 |
+
16,self_attn.o_proj,0.0000034948,0.05000,0.634
|
| 118 |
+
16,mlp.up_proj,0.0001171108,0.05000,0.645
|
| 119 |
+
16,mlp.gate_proj,0.0001227288,0.05000,0.646
|
| 120 |
+
16,mlp.down_proj,0.0000066009,0.05000,1.835
|
| 121 |
+
17,self_attn.k_proj,0.0000390972,0.05000,0.630
|
| 122 |
+
17,self_attn.v_proj,0.0000088621,0.05000,0.625
|
| 123 |
+
17,self_attn.q_proj,0.0000957747,0.05000,0.631
|
| 124 |
+
17,self_attn.o_proj,0.0000028237,0.05000,0.627
|
| 125 |
+
17,mlp.up_proj,0.0001155155,0.05000,0.639
|
| 126 |
+
17,mlp.gate_proj,0.0001188783,0.05000,0.630
|
| 127 |
+
17,mlp.down_proj,0.0000068800,0.05000,1.826
|
| 128 |
+
18,self_attn.k_proj,0.0000401956,0.05000,0.627
|
| 129 |
+
18,self_attn.v_proj,0.0000090248,0.05000,0.623
|
| 130 |
+
18,self_attn.q_proj,0.0000949841,0.05000,0.623
|
| 131 |
+
18,self_attn.o_proj,0.0000037460,0.05000,0.627
|
| 132 |
+
18,mlp.up_proj,0.0001139680,0.05000,0.646
|
| 133 |
+
18,mlp.gate_proj,0.0001146092,0.05000,0.629
|
| 134 |
+
18,mlp.down_proj,0.0000071555,0.05000,1.815
|
| 135 |
+
19,self_attn.k_proj,0.0000402539,0.05000,0.628
|
| 136 |
+
19,self_attn.v_proj,0.0000139554,0.05000,0.622
|
| 137 |
+
19,self_attn.q_proj,0.0001068750,0.05000,0.630
|
| 138 |
+
19,self_attn.o_proj,0.0000038656,0.05000,0.631
|
| 139 |
+
19,mlp.up_proj,0.0001136420,0.05000,0.642
|
| 140 |
+
19,mlp.gate_proj,0.0001112846,0.05000,0.639
|
| 141 |
+
19,mlp.down_proj,0.0000071713,0.05000,2.952
|
| 142 |
+
20,self_attn.k_proj,0.0000430777,0.05000,0.626
|
| 143 |
+
20,self_attn.v_proj,0.0000142388,0.05000,0.636
|
| 144 |
+
20,self_attn.q_proj,0.0001227000,0.05000,0.642
|
| 145 |
+
20,self_attn.o_proj,0.0000030897,0.05000,0.645
|
| 146 |
+
20,mlp.up_proj,0.0001152159,0.05000,0.640
|
| 147 |
+
20,mlp.gate_proj,0.0001108509,0.05000,0.630
|
| 148 |
+
20,mlp.down_proj,0.0000078913,0.05000,1.832
|
| 149 |
+
21,self_attn.k_proj,0.0000347235,0.05000,0.635
|
| 150 |
+
21,self_attn.v_proj,0.0000144389,0.05000,0.640
|
| 151 |
+
21,self_attn.q_proj,0.0000993896,0.05000,0.643
|
| 152 |
+
21,self_attn.o_proj,0.0000045465,0.05000,0.634
|
| 153 |
+
21,mlp.up_proj,0.0001203708,0.05000,0.640
|
| 154 |
+
21,mlp.gate_proj,0.0001146880,0.05000,0.649
|
| 155 |
+
21,mlp.down_proj,0.0000093812,0.05000,1.885
|
| 156 |
+
22,self_attn.k_proj,0.0000393358,0.05000,0.628
|
| 157 |
+
22,self_attn.v_proj,0.0000158499,0.05000,0.620
|
| 158 |
+
22,self_attn.q_proj,0.0001072611,0.05000,0.628
|
| 159 |
+
22,self_attn.o_proj,0.0000038499,0.05000,0.684
|
| 160 |
+
22,mlp.up_proj,0.0001163187,0.05000,0.647
|
| 161 |
+
22,mlp.gate_proj,0.0001113148,0.05000,0.664
|
| 162 |
+
22,mlp.down_proj,0.0000112921,0.05000,1.811
|
| 163 |
+
23,self_attn.k_proj,0.0000376413,0.05000,0.675
|
| 164 |
+
23,self_attn.v_proj,0.0000225085,0.05000,0.622
|
| 165 |
+
23,self_attn.q_proj,0.0001206446,0.05000,0.630
|
| 166 |
+
23,self_attn.o_proj,0.0000051591,0.05000,0.629
|
| 167 |
+
23,mlp.up_proj,0.0001291948,0.05000,0.634
|
| 168 |
+
23,mlp.gate_proj,0.0001304205,0.05000,0.633
|
| 169 |
+
23,mlp.down_proj,0.0000124118,0.05000,1.833
|
| 170 |
+
24,self_attn.k_proj,0.0000431973,0.05000,0.666
|
| 171 |
+
24,self_attn.v_proj,0.0000209506,0.05000,0.661
|
| 172 |
+
24,self_attn.q_proj,0.0001198867,0.05000,1.045
|
| 173 |
+
24,self_attn.o_proj,0.0000039563,0.05000,1.223
|
| 174 |
+
24,mlp.up_proj,0.0001520708,0.05000,0.642
|
| 175 |
+
24,mlp.gate_proj,0.0001611526,0.05000,0.636
|
| 176 |
+
24,mlp.down_proj,0.0000160874,0.05000,1.871
|
| 177 |
+
25,self_attn.k_proj,0.0000444450,0.05000,0.628
|
| 178 |
+
25,self_attn.v_proj,0.0000218121,0.05000,0.626
|
| 179 |
+
25,self_attn.q_proj,0.0001167302,0.05000,0.628
|
| 180 |
+
25,self_attn.o_proj,0.0000038277,0.05000,0.632
|
| 181 |
+
25,mlp.up_proj,0.0001813666,0.05000,0.708
|
| 182 |
+
25,mlp.gate_proj,0.0002004328,0.05000,0.738
|
| 183 |
+
25,mlp.down_proj,0.0000227922,0.05000,1.876
|
| 184 |
+
26,self_attn.k_proj,0.0000454051,0.05000,0.634
|
| 185 |
+
26,self_attn.v_proj,0.0000250637,0.05000,0.626
|
| 186 |
+
26,self_attn.q_proj,0.0001315469,0.05000,0.632
|
| 187 |
+
26,self_attn.o_proj,0.0000038909,0.05000,0.635
|
| 188 |
+
26,mlp.up_proj,0.0002314060,0.05000,0.665
|
| 189 |
+
26,mlp.gate_proj,0.0002628443,0.05000,0.627
|
| 190 |
+
26,mlp.down_proj,0.0000352535,0.05000,1.851
|
| 191 |
+
27,self_attn.k_proj,0.0000520552,0.05000,0.627
|
| 192 |
+
27,self_attn.v_proj,0.0000402771,0.05000,0.624
|
| 193 |
+
27,self_attn.q_proj,0.0001489883,0.05000,0.631
|
| 194 |
+
27,self_attn.o_proj,0.0000069768,0.05000,0.630
|
| 195 |
+
27,mlp.up_proj,0.0002660490,0.05000,0.637
|
| 196 |
+
27,mlp.gate_proj,0.0003050386,0.05000,0.635
|
| 197 |
+
27,mlp.down_proj,0.0000435111,0.05000,1.844
|
| 198 |
+
28,self_attn.k_proj,0.0000636018,0.05000,0.648
|
| 199 |
+
28,self_attn.v_proj,0.0000464218,0.05000,0.640
|
| 200 |
+
28,self_attn.q_proj,0.0001595764,0.05000,0.642
|
| 201 |
+
28,self_attn.o_proj,0.0000044354,0.05000,0.630
|
| 202 |
+
28,mlp.up_proj,0.0003046133,0.05000,0.640
|
| 203 |
+
28,mlp.gate_proj,0.0003516560,0.05000,0.645
|
| 204 |
+
28,mlp.down_proj,0.0000525115,0.05000,1.830
|
| 205 |
+
29,self_attn.k_proj,0.0000582551,0.05000,0.623
|
| 206 |
+
29,self_attn.v_proj,0.0000586798,0.05000,0.619
|
| 207 |
+
29,self_attn.q_proj,0.0001678434,0.05000,0.628
|
| 208 |
+
29,self_attn.o_proj,0.0000052813,0.05000,0.630
|
| 209 |
+
29,mlp.up_proj,0.0003163021,0.05000,0.637
|
| 210 |
+
29,mlp.gate_proj,0.0003633714,0.05000,0.630
|
| 211 |
+
29,mlp.down_proj,0.0000585934,0.05000,1.828
|
| 212 |
+
30,self_attn.k_proj,0.0000629496,0.05000,0.634
|
| 213 |
+
30,self_attn.v_proj,0.0000878309,0.05000,0.626
|
| 214 |
+
30,self_attn.q_proj,0.0001828223,0.05000,0.633
|
| 215 |
+
30,self_attn.o_proj,0.0000085314,0.05000,0.643
|
| 216 |
+
30,mlp.up_proj,0.0003682175,0.05000,0.649
|
| 217 |
+
30,mlp.gate_proj,0.0004197332,0.05000,0.641
|
| 218 |
+
30,mlp.down_proj,0.0000743252,0.05000,1.845
|
| 219 |
+
31,self_attn.k_proj,0.0000650040,0.05000,0.643
|
| 220 |
+
31,self_attn.v_proj,0.0000754176,0.05000,0.824
|
| 221 |
+
31,self_attn.q_proj,0.0001893100,0.05000,0.650
|
| 222 |
+
31,self_attn.o_proj,0.0000103287,0.05000,0.651
|
| 223 |
+
31,mlp.up_proj,0.0004369554,0.05000,0.659
|
| 224 |
+
31,mlp.gate_proj,0.0004915606,0.05000,0.651
|
| 225 |
+
31,mlp.down_proj,0.0001040258,0.05000,1.908
|
| 226 |
+
32,self_attn.k_proj,0.0000666418,0.05000,0.661
|
| 227 |
+
32,self_attn.v_proj,0.0001200235,0.05000,0.625
|
| 228 |
+
32,self_attn.q_proj,0.0001955563,0.05000,0.632
|
| 229 |
+
32,self_attn.o_proj,0.0000137284,0.05000,0.637
|
| 230 |
+
32,mlp.up_proj,0.0005367029,0.05000,0.639
|
| 231 |
+
32,mlp.gate_proj,0.0005717735,0.05000,0.630
|
| 232 |
+
32,mlp.down_proj,0.0001500942,0.05000,1.845
|
| 233 |
+
33,self_attn.k_proj,0.0000624501,0.05000,0.730
|
| 234 |
+
33,self_attn.v_proj,0.0000973847,0.05000,0.722
|
| 235 |
+
33,self_attn.q_proj,0.0002219080,0.05000,0.734
|
| 236 |
+
33,self_attn.o_proj,0.0000225097,0.05000,1.050
|
| 237 |
+
33,mlp.up_proj,0.0006794507,0.05000,1.144
|
| 238 |
+
33,mlp.gate_proj,0.0006961657,0.05000,1.150
|
| 239 |
+
33,mlp.down_proj,0.0002444487,0.05000,3.006
|
| 240 |
+
34,self_attn.k_proj,0.0000611097,0.05000,0.629
|
| 241 |
+
34,self_attn.v_proj,0.0001815660,0.05000,0.644
|
| 242 |
+
34,self_attn.q_proj,0.0002258574,0.05000,0.634
|
| 243 |
+
34,self_attn.o_proj,0.0000489831,0.05000,0.654
|
| 244 |
+
34,mlp.up_proj,0.0007841859,0.05000,1.177
|
| 245 |
+
34,mlp.gate_proj,0.0008123956,0.05000,1.276
|
| 246 |
+
34,mlp.down_proj,0.0003654951,0.05000,1.855
|
| 247 |
+
35,self_attn.k_proj,0.0000610122,0.05000,0.629
|
| 248 |
+
35,self_attn.v_proj,0.0001826982,0.05000,0.631
|
| 249 |
+
35,self_attn.q_proj,0.0002239264,0.05000,0.626
|
| 250 |
+
35,self_attn.o_proj,0.0000594668,0.05000,0.633
|
| 251 |
+
35,mlp.up_proj,0.0008546749,0.05000,0.652
|
| 252 |
+
35,mlp.gate_proj,0.0008875874,0.05000,0.635
|
| 253 |
+
35,mlp.down_proj,0.0007649885,0.05000,1.860
|
quantize_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"hyb_act": false,
|
| 6 |
+
"sym": true,
|
| 7 |
+
"lm_head": false,
|
| 8 |
+
"quant_method": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"pack_dtype": "int32",
|
| 11 |
+
"meta": {
|
| 12 |
+
"quantizer": [
|
| 13 |
+
"gptqmodel:4.0.0-dev"
|
| 14 |
+
],
|
| 15 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 16 |
+
"damp_percent": 0.05,
|
| 17 |
+
"damp_auto_increment": 0.01,
|
| 18 |
+
"static_groups": false,
|
| 19 |
+
"true_sequential": true,
|
| 20 |
+
"mse": 0.0,
|
| 21 |
+
"v2": false,
|
| 22 |
+
"v2_alpha": 0.25
|
| 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": "<|vision_pad|>"
|
| 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": "<|vision_pad|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 206 |
+
"unk_token": null,
|
| 207 |
+
"_commit_hash": null
|
| 208 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_pad": null,
|
| 10 |
+
"do_rescale": true,
|
| 11 |
+
"do_resize": true,
|
| 12 |
+
"do_sample_frames": false,
|
| 13 |
+
"fps": null,
|
| 14 |
+
"image_mean": [
|
| 15 |
+
0.48145466,
|
| 16 |
+
0.4578275,
|
| 17 |
+
0.40821073
|
| 18 |
+
],
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.26862954,
|
| 21 |
+
0.26130258,
|
| 22 |
+
0.27577711
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_frames": 768,
|
| 26 |
+
"max_pixels": 12845056,
|
| 27 |
+
"merge_size": 2,
|
| 28 |
+
"min_frames": 4,
|
| 29 |
+
"min_pixels": 3136,
|
| 30 |
+
"num_frames": null,
|
| 31 |
+
"patch_size": 14,
|
| 32 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 33 |
+
"resample": 3,
|
| 34 |
+
"rescale_factor": 0.00392156862745098,
|
| 35 |
+
"size": {
|
| 36 |
+
"longest_edge": 12845056,
|
| 37 |
+
"shortest_edge": 3136
|
| 38 |
+
},
|
| 39 |
+
"size_divisor": null,
|
| 40 |
+
"temporal_patch_size": 2,
|
| 41 |
+
"video_metadata": null,
|
| 42 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 43 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|