wtdcode commited on
Commit
fb5cd79
·
verified ·
1 Parent(s): c5bcd87

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
awq_run_info.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "args": {
3
+ "model": "/home/ziqiao/Qwen38-Flash-Next",
4
+ "out": "/home/ziqiao/awq-out/Qwen3.8-Flash-Next-AWQ-W4A16",
5
+ "num_samples": 256,
6
+ "seq_len": 2048,
7
+ "calib_source": "ultrachat",
8
+ "scheme": "W4A16",
9
+ "duo_scaling": "true",
10
+ "n_grid": 10,
11
+ "load": "cpu",
12
+ "offload_folder": "/home/ziqiao/tmp/offload_folder",
13
+ "no_pin_ngram": false,
14
+ "tiny": false,
15
+ "no_fast_indexer": false,
16
+ "no_fast_smoothing": false,
17
+ "dummy_modules": 0,
18
+ "calibrate_all_experts": "false",
19
+ "batch_size": 16,
20
+ "pack": "true",
21
+ "awq_cache": "gpu"
22
+ },
23
+ "seconds": 3092.242558002472
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set reasoning_instructions = '' %}
46
+ {%- if enable_thinking is undefined or enable_thinking is true %}
47
+ {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
48
+ {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
+ {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
+ {%- endif %}
51
+ {%- if resolved_reasoning_effort == 'xhigh' %}
52
+ {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
53
+ {%- elif resolved_reasoning_effort == 'low' %}
54
+ {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if tools and tools is iterable and tools is not mapping %}
58
+ {{- '<|im_start|>system\n' }}
59
+ {%- if reasoning_instructions %}
60
+ {{- reasoning_instructions + '\n\n' }}
61
+ {%- endif %}
62
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
+ {%- for tool in tools %}
64
+ {{- "\n" }}
65
+ {{- tool | tojson }}
66
+ {%- endfor %}
67
+ {{- "\n</tools>" }}
68
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
69
+ {%- if messages[0].role == 'system' %}
70
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
71
+ {%- if content %}
72
+ {{- '\n\n' + content }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {{- '<|im_end|>\n' }}
76
+ {%- else %}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
+ {%- elif reasoning_instructions %}
82
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
+ {%- endif %}
84
+ {%- elif reasoning_instructions %}
85
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
88
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
+ {%- for message in messages[::-1] %}
90
+ {%- set index = (messages|length - 1) - loop.index0 %}
91
+ {%- if ns.multi_step_tool and message.role == "user" %}
92
+ {%- set content = render_content(message.content, false)|trim %}
93
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
+ {%- set ns.multi_step_tool = false %}
95
+ {%- set ns.last_query_index = index %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+ {%- endfor %}
99
+ {%- if ns.multi_step_tool %}
100
+ {{- raise_exception('No user query found in messages.') }}
101
+ {%- endif %}
102
+ {%- for message in messages %}
103
+ {%- set content = render_content(message.content, true)|trim %}
104
+ {%- if message.role == "system" %}
105
+ {%- if not loop.first %}
106
+ {{- raise_exception('System message must be at the beginning.') }}
107
+ {%- endif %}
108
+ {%- elif message.role == "user" %}
109
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
+ {%- elif message.role == "assistant" %}
111
+ {%- set reasoning_content = '' %}
112
+ {%- if message.reasoning_content is string %}
113
+ {%- set reasoning_content = message.reasoning_content %}
114
+ {%- endif %}
115
+ {%- set reasoning_content = reasoning_content|trim %}
116
+ {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
+ {%- else %}
119
+ {{- '<|im_start|>' + message.role + '\n' + content }}
120
+ {%- endif %}
121
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
+ {%- for tool_call in message.tool_calls %}
123
+ {%- if tool_call.function is defined %}
124
+ {%- set tool_call = tool_call.function %}
125
+ {%- endif %}
126
+ {%- if loop.first %}
127
+ {%- if content|trim %}
128
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
+ {%- else %}
130
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
+ {%- endif %}
135
+ {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
+ {%- for args_name, args_value in tool_call.arguments|items %}
137
+ {{- '<parameter=' + args_name + '>\n' }}
138
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
+ {{- args_value }}
140
+ {{- '\n</parameter>\n' }}
141
+ {%- endfor %}
142
+ {%- endif %}
143
+ {{- '</function>\n</tool_call>' }}
144
+ {%- endfor %}
145
+ {%- endif %}
146
+ {{- '<|im_end|>\n' }}
147
+ {%- elif message.role == "tool" %}
148
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
149
+ {{- '<|im_start|>user' }}
150
+ {%- endif %}
151
+ {{- '\n<tool_response>\n' }}
152
+ {{- content }}
153
+ {{- '\n</tool_response>' }}
154
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif loop.last %}
157
+ {{- '<|im_end|>\n' }}
158
+ {%- endif %}
159
+ {%- else %}
160
+ {{- raise_exception('Unexpected message role.') }}
161
+ {%- endif %}
162
+ {%- endfor %}
163
+ {%- if add_generation_prompt %}
164
+ {{- '<|im_start|>assistant\n' }}
165
+ {%- if enable_thinking is defined and enable_thinking is false %}
166
+ {{- '<think>\n\n</think>\n\n' }}
167
+ {%- else %}
168
+ {{- '<think>\n' }}
169
+ {%- endif %}
170
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen4ExpForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "language_model_only": false,
8
+ "model_type": "qwen4_exp",
9
+ "quantization_config": {
10
+ "config_groups": {
11
+ "group_0": {
12
+ "format": "pack-quantized",
13
+ "input_activations": null,
14
+ "output_activations": null,
15
+ "targets": [
16
+ "Linear"
17
+ ],
18
+ "weights": {
19
+ "actorder": null,
20
+ "block_structure": null,
21
+ "dynamic": false,
22
+ "group_size": 128,
23
+ "num_bits": 4,
24
+ "observer": "memoryless_minmax",
25
+ "observer_kwargs": {},
26
+ "scale_dtype": null,
27
+ "strategy": "group",
28
+ "symmetric": true,
29
+ "type": "int",
30
+ "zp_dtype": null
31
+ }
32
+ }
33
+ },
34
+ "format": "pack-quantized",
35
+ "global_compression_ratio": null,
36
+ "ignore": [
37
+ "lm_head",
38
+ "re:.*embed_tokens.*",
39
+ "re:.*mtp\\..*",
40
+ "re:^mtp.*",
41
+ "re:.*\\.ple\\..*",
42
+ "re:.*visual\\..*",
43
+ "re:.*\\.gate$",
44
+ "re:.*hyper_connection.*",
45
+ "re:.*indexer.*",
46
+ "re:.*\\.linear_attn\\..*",
47
+ "re:.*self_attn\\..*",
48
+ "re:.*shared_expert.*"
49
+ ],
50
+ "kv_cache_scheme": null,
51
+ "quant_method": "compressed-tensors",
52
+ "quantization_status": "compressed",
53
+ "sparsity_config": {},
54
+ "transform_config": {},
55
+ "version": "0.18.1.a20260826"
56
+ },
57
+ "text_config": {
58
+ "attention_bias": false,
59
+ "attention_dropout": 0.0,
60
+ "bos_token_id": 248044,
61
+ "dtype": "bfloat16",
62
+ "eos_token_id": 248044,
63
+ "full_attention_interval": 4,
64
+ "hc_count": 4,
65
+ "hc_lowrank": 320,
66
+ "head_dim": 256,
67
+ "heads_per_ngram": 8,
68
+ "hidden_act": "silu",
69
+ "hidden_size": 2560,
70
+ "indexer_budget": 2048,
71
+ "indexer_compress_ratio": 4,
72
+ "indexer_head_dim": 128,
73
+ "indexer_kv_heads": 1,
74
+ "indexer_n_heads": 4,
75
+ "initializer_range": 0.02,
76
+ "layer_types": [
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "qwen_sparse_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "qwen_sparse_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "qwen_sparse_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "qwen_sparse_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "linear_attention",
96
+ "qwen_sparse_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "linear_attention",
100
+ "qwen_sparse_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "linear_attention",
104
+ "qwen_sparse_attention",
105
+ "linear_attention",
106
+ "linear_attention",
107
+ "linear_attention",
108
+ "qwen_sparse_attention",
109
+ "linear_attention",
110
+ "linear_attention",
111
+ "linear_attention",
112
+ "qwen_sparse_attention",
113
+ "linear_attention",
114
+ "linear_attention",
115
+ "linear_attention",
116
+ "qwen_sparse_attention",
117
+ "linear_attention",
118
+ "linear_attention",
119
+ "linear_attention",
120
+ "qwen_sparse_attention",
121
+ "linear_attention",
122
+ "linear_attention",
123
+ "linear_attention",
124
+ "qwen_sparse_attention"
125
+ ],
126
+ "linear_conv_kernel_dim": 4,
127
+ "linear_key_head_dim": 128,
128
+ "linear_num_key_heads": 16,
129
+ "linear_num_value_heads": 48,
130
+ "linear_value_head_dim": 128,
131
+ "make_ngram_vocab_size_divisible_by": 128,
132
+ "mamba_ssm_dtype": "float32",
133
+ "max_position_embeddings": 262144,
134
+ "model_type": "qwen4_exp_text",
135
+ "moe_intermediate_size": 640,
136
+ "mtp": {
137
+ "hybrid": true,
138
+ "layer_types": [
139
+ "full_attention"
140
+ ],
141
+ "mtp_use_hidden_state_from_layer": null,
142
+ "num_hidden_layers": 1,
143
+ "rope_theta": 10000000
144
+ },
145
+ "mtp_num_hidden_layers": 1,
146
+ "mtp_use_dedicated_embeddings": false,
147
+ "ngram_size": 3,
148
+ "ngram_vocab_size_base": 20000000,
149
+ "norm_topk_prob": true,
150
+ "num_attention_heads": 24,
151
+ "num_experts": 512,
152
+ "num_experts_per_tok": 10,
153
+ "num_hidden_layers": 48,
154
+ "num_key_value_heads": 2,
155
+ "number_of_conv_states": 3,
156
+ "output_gate_type": "sigmoid",
157
+ "output_router_logits": false,
158
+ "pad_token_id": null,
159
+ "partial_rotary_factor": 0.25,
160
+ "ple_conv_kernel_size": 4,
161
+ "ple_embed_dim": 2560,
162
+ "ple_layer_ids": [
163
+ 2
164
+ ],
165
+ "rms_norm_eps": 1e-06,
166
+ "rope_parameters": {
167
+ "mrope_interleaved": true,
168
+ "mrope_section": [
169
+ 11,
170
+ 11,
171
+ 10
172
+ ],
173
+ "partial_rotary_factor": 0.25,
174
+ "rope_theta": 10000000,
175
+ "rope_type": "default"
176
+ },
177
+ "router_aux_loss_coef": 0.001,
178
+ "seed": 1234,
179
+ "shared_expert_intermediate_size": 640,
180
+ "split_ngram_parts": 128,
181
+ "tie_word_embeddings": false,
182
+ "use_cache": true,
183
+ "vocab_size": 248320
184
+ },
185
+ "tie_word_embeddings": false,
186
+ "transformers_version": "5.16.1",
187
+ "video_token_id": 248057,
188
+ "vision_config": {
189
+ "deepstack_visual_indexes": [],
190
+ "depth": 27,
191
+ "dtype": "bfloat16",
192
+ "hidden_act": "gelu_pytorch_tanh",
193
+ "hidden_size": 1152,
194
+ "in_channels": 3,
195
+ "initializer_range": 0.02,
196
+ "intermediate_size": 4304,
197
+ "model_type": "qwen4_exp_vision",
198
+ "num_heads": 16,
199
+ "num_position_embeddings": 2304,
200
+ "out_hidden_size": 2560,
201
+ "patch_size": 16,
202
+ "spatial_merge_size": 2,
203
+ "temporal_patch_size": 2
204
+ },
205
+ "vision_end_token_id": 248054,
206
+ "vision_start_token_id": 248053
207
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.16.1"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64836044b0d06b54a3a1f3fd3cf4ce06ba005fb6319abb100479b7a151f7f44c
3
+ size 102400512288
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb830243a6f1f56f8849cdc829724383c3fa104ba793e7f879a19927d4e8a32
3
+ size 20007503112
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b849022ecb3fae6c8d6cdde768da899abb47c25bfc44d87e8c931f11b124cb
3
+ size 19960933248
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af83800aeef9ee47e49fc0a9769f67617108934626e79a2e30051ef48f338a7d
3
+ size 20008579224
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e2d8c38b466774703b831ccbfc89f1c78e726d2296bb7eaaf2d3b31933fadd
3
+ size 13134032728
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36a6c9ca3edacd0b652c45d4efbf9f11493b87f598d1d252a0b0397d43a7d69
3
+ size 24987506
model_mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f346d471136314ebe66af5193c0a01fd00ffdc22a4a8c9f86bd15948bc9a8212
3
+ size 5214305424
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
processor_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "max_video_tokens": 768,
48
+ "merge_size": 2,
49
+ "min_frames": 4,
50
+ "patch_size": 16,
51
+ "resample": 3,
52
+ "rescale_factor": 0.00392156862745098,
53
+ "return_metadata": false,
54
+ "size": {
55
+ "longest_edge": 25165824,
56
+ "shortest_edge": 4096
57
+ },
58
+ "temporal_patch_size": 2,
59
+ "video_processor_type": "Qwen3VLVideoProcessor"
60
+ }
61
+ }
recipe.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ AWQModifier:
4
+ requires_calibration_data: true
5
+ mappings:
6
+ - smooth_layer: re:.*mlp\.experts\.\d+\.up_proj$
7
+ balance_layers: ['re:.*mlp\.experts\.\d+\.down_proj$']
8
+ activation_hook_target: null
9
+ duo_scaling: true
10
+ n_grid: 10
11
+ QuantizationModifier:
12
+ targets: ['re:.*mlp\.experts\.\d+\.(gate_proj|up_proj|down_proj)$']
13
+ ignore: [lm_head, 're:.*embed_tokens.*', 're:.*mtp\..*', 're:.*\.ple\..*', 're:.*visual\..*',
14
+ 're:.*\.gate$', 're:.*hyper_connection.*', 're:.*indexer.*', 're:.*\.linear_attn\..*',
15
+ 're:.*self_attn\..*', 're:.*shared_expert.*']
16
+ scheme: W4A16
17
+ bypass_divisibility_checks: false
18
+ requires_calibration_data: false
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
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": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
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": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }