PolarQuant v7: GPTQ INT4 gs64 + FOEM | 27B | Marlin native
Browse files- .gitattributes +1 -0
- chat_template.jinja +88 -0
- config.json +200 -0
- generation_config.json +10 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor_config.json +63 -0
- quantize_config.json +48 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -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
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant
|
| 86 |
+
<think>
|
| 87 |
+
' }}
|
| 88 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248046,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_name": "unsloth/Qwen3.5-27B",
|
| 10 |
+
"model_type": "qwen3_5",
|
| 11 |
+
"pad_token_id": 248055,
|
| 12 |
+
"quantization_config": {
|
| 13 |
+
"bits": 4,
|
| 14 |
+
"checkpoint_format": "gptq",
|
| 15 |
+
"desc_act": true,
|
| 16 |
+
"format": "gptq",
|
| 17 |
+
"group_size": 64,
|
| 18 |
+
"lm_head": false,
|
| 19 |
+
"meta": {
|
| 20 |
+
"act_group_aware": false,
|
| 21 |
+
"auto_forward_data_parallel": true,
|
| 22 |
+
"damp_auto_increment": 0.01,
|
| 23 |
+
"damp_percent": 0.05,
|
| 24 |
+
"fallback": {
|
| 25 |
+
"smooth": null,
|
| 26 |
+
"strategy": "rtn",
|
| 27 |
+
"threshold": "0.5%"
|
| 28 |
+
},
|
| 29 |
+
"foem": {
|
| 30 |
+
"alpha": 0.25,
|
| 31 |
+
"beta": 0.2,
|
| 32 |
+
"device": "auto"
|
| 33 |
+
},
|
| 34 |
+
"gc_mode": "interval",
|
| 35 |
+
"gptaq": null,
|
| 36 |
+
"hessian": {
|
| 37 |
+
"chunk_bytes": null,
|
| 38 |
+
"chunk_size": null,
|
| 39 |
+
"staging_dtype": "float32"
|
| 40 |
+
},
|
| 41 |
+
"mock_quantization": false,
|
| 42 |
+
"mse": 0.0,
|
| 43 |
+
"offload_to_disk": true,
|
| 44 |
+
"offload_to_disk_path": "./gptqmodel_offload/txweqvph-winziehw/",
|
| 45 |
+
"pack_impl": "cpu",
|
| 46 |
+
"quantizer": [
|
| 47 |
+
"gptqmodel:6.0.3"
|
| 48 |
+
],
|
| 49 |
+
"static_groups": false,
|
| 50 |
+
"true_sequential": true,
|
| 51 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 52 |
+
"vram_strategy": "exclusive",
|
| 53 |
+
"wait_for_submodule_finalizers": false
|
| 54 |
+
},
|
| 55 |
+
"method": "gptq",
|
| 56 |
+
"pack_dtype": "int32",
|
| 57 |
+
"quant_method": "gptq",
|
| 58 |
+
"sym": true
|
| 59 |
+
},
|
| 60 |
+
"rope_parameters": {
|
| 61 |
+
"rope_theta": 10000.0,
|
| 62 |
+
"rope_type": "default"
|
| 63 |
+
},
|
| 64 |
+
"text_config": {
|
| 65 |
+
"attention_bias": false,
|
| 66 |
+
"attention_dropout": 0.0,
|
| 67 |
+
"attn_output_gate": true,
|
| 68 |
+
"bos_token_id": null,
|
| 69 |
+
"dtype": "bfloat16",
|
| 70 |
+
"eos_token_id": 248044,
|
| 71 |
+
"full_attention_interval": 4,
|
| 72 |
+
"head_dim": 256,
|
| 73 |
+
"hidden_act": "silu",
|
| 74 |
+
"hidden_size": 5120,
|
| 75 |
+
"initializer_range": 0.02,
|
| 76 |
+
"intermediate_size": 17408,
|
| 77 |
+
"layer_types": [
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"linear_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"linear_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"linear_attention",
|
| 91 |
+
"linear_attention",
|
| 92 |
+
"linear_attention",
|
| 93 |
+
"full_attention",
|
| 94 |
+
"linear_attention",
|
| 95 |
+
"linear_attention",
|
| 96 |
+
"linear_attention",
|
| 97 |
+
"full_attention",
|
| 98 |
+
"linear_attention",
|
| 99 |
+
"linear_attention",
|
| 100 |
+
"linear_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"linear_attention",
|
| 103 |
+
"linear_attention",
|
| 104 |
+
"linear_attention",
|
| 105 |
+
"full_attention",
|
| 106 |
+
"linear_attention",
|
| 107 |
+
"linear_attention",
|
| 108 |
+
"linear_attention",
|
| 109 |
+
"full_attention",
|
| 110 |
+
"linear_attention",
|
| 111 |
+
"linear_attention",
|
| 112 |
+
"linear_attention",
|
| 113 |
+
"full_attention",
|
| 114 |
+
"linear_attention",
|
| 115 |
+
"linear_attention",
|
| 116 |
+
"linear_attention",
|
| 117 |
+
"full_attention",
|
| 118 |
+
"linear_attention",
|
| 119 |
+
"linear_attention",
|
| 120 |
+
"linear_attention",
|
| 121 |
+
"full_attention",
|
| 122 |
+
"linear_attention",
|
| 123 |
+
"linear_attention",
|
| 124 |
+
"linear_attention",
|
| 125 |
+
"full_attention",
|
| 126 |
+
"linear_attention",
|
| 127 |
+
"linear_attention",
|
| 128 |
+
"linear_attention",
|
| 129 |
+
"full_attention",
|
| 130 |
+
"linear_attention",
|
| 131 |
+
"linear_attention",
|
| 132 |
+
"linear_attention",
|
| 133 |
+
"full_attention",
|
| 134 |
+
"linear_attention",
|
| 135 |
+
"linear_attention",
|
| 136 |
+
"linear_attention",
|
| 137 |
+
"full_attention",
|
| 138 |
+
"linear_attention",
|
| 139 |
+
"linear_attention",
|
| 140 |
+
"linear_attention",
|
| 141 |
+
"full_attention"
|
| 142 |
+
],
|
| 143 |
+
"linear_conv_kernel_dim": 4,
|
| 144 |
+
"linear_key_head_dim": 128,
|
| 145 |
+
"linear_num_key_heads": 16,
|
| 146 |
+
"linear_num_value_heads": 48,
|
| 147 |
+
"linear_value_head_dim": 128,
|
| 148 |
+
"mamba_ssm_dtype": "float32",
|
| 149 |
+
"max_position_embeddings": 262144,
|
| 150 |
+
"mlp_only_layers": [],
|
| 151 |
+
"model_type": "qwen3_5_text",
|
| 152 |
+
"mtp_num_hidden_layers": 1,
|
| 153 |
+
"mtp_use_dedicated_embeddings": false,
|
| 154 |
+
"num_attention_heads": 24,
|
| 155 |
+
"num_hidden_layers": 64,
|
| 156 |
+
"num_key_value_heads": 4,
|
| 157 |
+
"pad_token_id": 248055,
|
| 158 |
+
"partial_rotary_factor": 0.25,
|
| 159 |
+
"rms_norm_eps": 1e-06,
|
| 160 |
+
"rope_parameters": {
|
| 161 |
+
"mrope_interleaved": true,
|
| 162 |
+
"mrope_section": [
|
| 163 |
+
11,
|
| 164 |
+
11,
|
| 165 |
+
10
|
| 166 |
+
],
|
| 167 |
+
"partial_rotary_factor": 0.25,
|
| 168 |
+
"rope_theta": 10000000,
|
| 169 |
+
"rope_type": "default"
|
| 170 |
+
},
|
| 171 |
+
"tie_word_embeddings": false,
|
| 172 |
+
"use_cache": true,
|
| 173 |
+
"vocab_size": 248320
|
| 174 |
+
},
|
| 175 |
+
"tie_word_embeddings": false,
|
| 176 |
+
"transformers_version": "5.5.0",
|
| 177 |
+
"unsloth_fixed": true,
|
| 178 |
+
"unsloth_version": "2026.3.18",
|
| 179 |
+
"use_cache": false,
|
| 180 |
+
"video_token_id": 248057,
|
| 181 |
+
"vision_config": {
|
| 182 |
+
"deepstack_visual_indexes": [],
|
| 183 |
+
"depth": 27,
|
| 184 |
+
"dtype": "bfloat16",
|
| 185 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 186 |
+
"hidden_size": 1152,
|
| 187 |
+
"in_channels": 3,
|
| 188 |
+
"initializer_range": 0.02,
|
| 189 |
+
"intermediate_size": 4304,
|
| 190 |
+
"model_type": "qwen3_5",
|
| 191 |
+
"num_heads": 16,
|
| 192 |
+
"num_position_embeddings": 2304,
|
| 193 |
+
"out_hidden_size": 5120,
|
| 194 |
+
"patch_size": 16,
|
| 195 |
+
"spatial_merge_size": 2,
|
| 196 |
+
"temporal_patch_size": 2
|
| 197 |
+
},
|
| 198 |
+
"vision_end_token_id": 248054,
|
| 199 |
+
"vision_start_token_id": 248053
|
| 200 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 248046,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 248055,
|
| 8 |
+
"transformers_version": "5.5.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9cfb211562bed27079adfd7257edda031d12ede7830c6148470101bd4f7fa5
|
| 3 |
+
size 3516829256
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5082d0bf96b50630c12903cf96b2cf3190f9c890ae282a6189a44e6ccd815e6e
|
| 3 |
+
size 4293823984
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:808eef11fb72773d0994c1f2fb8a0bf37cd3c7b907df75559e0ba624685bbcb9
|
| 3 |
+
size 4262950792
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:555b605174a39865b53087e0677cd5abbf4e2df8f62eb06006e1c312044d1f62
|
| 3 |
+
size 4289451816
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5692cdc61f5527b0fedd5934277e4d79d60fa5754301155665aa2922cd8c4216
|
| 3 |
+
size 2822130800
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
quantize_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 64,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"lm_head": false,
|
| 6 |
+
"method": "gptq",
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"format": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"pack_dtype": "int32",
|
| 11 |
+
"meta": {
|
| 12 |
+
"quantizer": [
|
| 13 |
+
"gptqmodel:6.0.3"
|
| 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 |
+
"gptaq": null,
|
| 22 |
+
"foem": {
|
| 23 |
+
"alpha": 0.25,
|
| 24 |
+
"beta": 0.2,
|
| 25 |
+
"device": "auto"
|
| 26 |
+
},
|
| 27 |
+
"act_group_aware": false,
|
| 28 |
+
"fallback": {
|
| 29 |
+
"strategy": "rtn",
|
| 30 |
+
"threshold": "0.5%",
|
| 31 |
+
"smooth": null
|
| 32 |
+
},
|
| 33 |
+
"offload_to_disk": true,
|
| 34 |
+
"offload_to_disk_path": "./gptqmodel_offload/txweqvph-winziehw/",
|
| 35 |
+
"pack_impl": "cpu",
|
| 36 |
+
"gc_mode": "interval",
|
| 37 |
+
"wait_for_submodule_finalizers": false,
|
| 38 |
+
"auto_forward_data_parallel": true,
|
| 39 |
+
"vram_strategy": "exclusive",
|
| 40 |
+
"mock_quantization": false,
|
| 41 |
+
"hessian": {
|
| 42 |
+
"chunk_size": null,
|
| 43 |
+
"chunk_bytes": null,
|
| 44 |
+
"staging_dtype": "float32"
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"sym": true
|
| 48 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd6b8cf757c22939ad262adb1077fa3b8e7cbb89054bc2507630b0f6aafd80ae
|
| 3 |
+
size 19989442
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|vision_pad|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|