ai-models/Qwen3.6-35B-A3B
2
0
Fork 0
mirror of https://www.modelscope.cn/Qwen/Qwen3.6-35B-A3B.git synced 2026-07-16 06:42:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upload to Qwen/Qwen3.6-35B-A3B on ModelScope hub (batch 1/1)

Browse Source
This commit is contained in:
VoyagerX
2026-04-16 13:04:14 +00:00
parent ca8b7eb399
commit 1a5ae24e86
38 changed files with 2835 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
.gitattributes vendored
View File

@ -45,3 +45,33 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text
model-00011-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00018-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
model-00005-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
model-00008-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00025-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00010-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00014-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00012-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00019-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00021-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00017-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00022-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00015-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00020-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00026-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00016-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00023-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00024-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text
model-00013-of-00026.safetensors filter=lfs diff=lfs merge=lfs -text

1079
README.md
View File

File diff suppressed because it is too large Load Diff

154
chat_template.jinja Normal file
View File

@ -0,0 +1,154 @@
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\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>' }}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" %}
{%- if not loop.first %}
{{- raise_exception('System message must be at the beginning.') }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- else %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}

119
config.json Normal file
View File

@ -0,0 +1,119 @@
{
"architectures": [
"Qwen3_5MoeForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5_moe",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": 248044,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"model_type": "qwen3_5_moe_text",
"moe_intermediate_size": 512,
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_experts": 256,
"num_experts_per_tok": 8,
"num_hidden_layers": 40,
"num_key_value_heads": 2,
"output_router_logits": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"router_aux_loss_coef": 0.001,
"shared_expert_intermediate_size": 512,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_5_moe",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2048,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}

12
generation_config.json Normal file
View File

@ -0,0 +1,12 @@
{
"bos_token_id": 248044,
"do_sample": true,
"eos_token_id": [
248046,
248044
],
"pad_token_id": 248044,
"temperature": 1.0,
"top_k": 20,
"top_p": 0.95
}

3
merges.txt Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
size 3353259

3
model-00001-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:adee7bcb930aed22e0677e58d4873b48dadb1ed8001cb5c6a0487286eadb3478
size 3996199712

3
model-00002-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88f2dfd2b9e73e4b70be533dbf61bcfa3c9a0003758900fcbc9d9b96f5751d4b
size 1284907696

3
model-00003-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f7d72178d3f4431864978e5bcfa4c6cb1c204bc00590644d90bb19d6d522eeb
size 3357898360

3
model-00004-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12d7db38689ba3c8af74b23ef8523eca41e0cd95db870583d0663a3ee8a6bd60
size 3370808712

3
model-00005-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a836047305d0f7a7b50f0815d09d5c03ec03d59ec2c763fcdc4bf7e9936bf902
size 3357898360

3
model-00006-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9080d718e9c5f9e337443225aa417d4c24d00ae7995d76ee3f1cc296b557d15
size 3959424904

3
model-00007-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8c05e23131b1dd45a455ec38cfac7db14667358268623c3938d00cf3e959a68
size 1096788232

3
model-00008-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b6a6d495053089f4a80e7cbc82e848fba44e2c0c60122233d8fdff79fa7b296
size 3946842008

3
model-00009-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a31a954bb72d1c714e751bf0aabf2ff533f5a509693ebf7dd22ad6e90be46f67
size 1096460848

3
model-00010-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:246560e66570fe746653b8443e245dc334c9b8b831ea43d2d9f1b7d98623994e
size 3946841992

3
model-00011-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7180392817fe3ecb3a27a1da43b7ff22c1a94806bac49975f9f122c3126df675
size 1096460752

3
model-00012-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:043fb525f6625c2f2acb75e65a9959ee3fa7b6e3fdd2034b5cfe1859b01d3cfb
size 3409971080

3
model-00013-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33a20fb20a21379bf43c84a43105f9c0cc35bd50d740b1c302dcbe4b700f5425
size 1633331664

3
model-00014-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be823e33c5cb6120ad3769d081f34a2449dc2358041fca7c29d636c1ba19130d
size 3422553872

3
model-00015-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a89d547c6f9d0b535ee5ea2f2478f163089539f3f0dd330cb23d278a19d76123
size 1633659224

3
model-00016-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69fc3ae0316482288afdcdd0b9eb7d626703ae26f7567e89aa3fc8d1ffd4ff5b
size 3946842136

3
model-00017-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e356e3943cf3852b76bb8992e674f3256013e27d54b78e8250514151cdc29637
size 1096460608

3
model-00018-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e5e63fd1cc7d6848330c1fa363dfcb661bbc2ac87e672d0e28b71c9cb7f3c7f
size 3946841992

3
model-00019-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:708644ad34f1de727bf484f396944d8ec628645d52c183e9a992e65671685e21
size 1096460808

3
model-00020-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca083a1d1aa64f8e8a785998f543a43374f13436dc85d396eee4e72c7a84e1ae
size 3409971072

3
model-00021-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ada4ae48f3d48fe01b4c53f2f82bce25e798a9631fd33959c881156fef2ccbce
size 1633331744

3
model-00022-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:def207fb42d7db31efb512755557763c23233c6e4d4c433027cb5102a7bce2f7
size 3370808752

3
model-00023-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:864d52ca7768a36f514069222e8de8626264ae124097ba8fcce5b5da2c6e2ed7
size 3357898392

3
model-00024-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:391acd27420cdce5935ff18152423c70620d19dac3c39a5ef1a81d369f82d737
size 3370808752

3
model-00025-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:778e7f76602f05042b69ba7f3ec91f1fdffef390540b16074041c258fb81d154
size 3832888256

3
model-00026-of-00026.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a97404220077ed3d4182e10385b152004cab608377f50cec9f54a6b8d28b613
size 2231416848

1052
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
preprocessor_config.json Normal file
View File

@ -0,0 +1,21 @@
{
"size": {
"longest_edge": 16777216,
"shortest_edge": 65536
},
"patch_size": 16,
"temporal_patch_size": 2,
"merge_size": 2,
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"processor_class": "Qwen3VLProcessor",
"image_processor_type": "Qwen2VLImageProcessorFast"
}

3
tokenizer.json Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
size 12807982

305
tokenizer_config.json Normal file
View File

File diff suppressed because one or more lines are too long

21
video_preprocessor_config.json Normal file
View File

@ -0,0 +1,21 @@
{
"size": {
"longest_edge": 25165824,
"shortest_edge": 4096
},
"patch_size": 16,
"temporal_patch_size": 2,
"merge_size": 2,
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"processor_class": "Qwen3VLProcessor",
"video_processor_type": "Qwen3VLVideoProcessor"
}

3
vocab.json Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
size 6722759