groupuser/Qwen3.5-9B
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upload folder using huggingface_hub

Browse Source
This commit is contained in:
cheng 2026-02-27 13:09:26 +00:00 committed by system
parent d45e68c4ae
commit 21eca8a083
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
14 changed files with 497001 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitattributes vendored
View File

@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text *.zip 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
tokenizer.json filter=lfs diff=lfs merge=lfs -text

120
chat_template.jinja Normal file
View File

@ -0,0 +1,120 @@
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count) %}
{%- if content is string %}
{{- content }}
{%- else %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- 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 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 }}
{%- endif %}
{%- endfor %}
{%- endif %}
{%- endmacro %}
{%- if tools is defined and tools is iterable and tools | length > 0 %}
{{- '<|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' and messages[0].content | trim %}
{%- set content = render_content(messages[0].content, false) %}
{{- '\n\n' + content.lstrip('\n') }}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|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) %}
{%- 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 %}
{%- for message in messages %}
{%- set content = render_content(message.content, true) %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- 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 %}
{%- if message.tool_calls is defined and message.tool_calls is not none and message.tool_calls is iterable and message.tool_calls | length > 0 %}
{%- set content = content.rstrip('\n') %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls is defined and message.tool_calls is not none and message.tool_calls is iterable and message.tool_calls | length > 0 %}
{%- 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
{{- 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 %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n<think>\n' }}
{%- endif %}

103
config.json Normal file
View File

@ -0,0 +1,103 @@
{
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"use_cache": true,
"vocab_size": 248320,
"mamba_ssm_dtype": "float32",
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
}
},
"tie_word_embeddings": false,
"transformers_version": "4.57.0.dev0",
"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",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 4096,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}

247587
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
model.safetensors-00001-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
model.safetensors-00002-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
model.safetensors-00003-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
model.safetensors-00004-of-00004.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

782
model.safetensors.index.json Normal file
View File

@ -0,0 +1,782 @@
{
"metadata": {
"total_size": 19306216416
},
"weight_map": {
"lm_head.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.25.mlp.down_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.26.mlp.down_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.26.mlp.gate_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.26.mlp.up_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.27.mlp.down_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.27.mlp.gate_proj.weight": "model.safetensors-00001-of-00004.safetensors",
"model.language_model.layers.27.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.30.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.30.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.30.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.31.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.31.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.31.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00002-of-00004.safetensors",
"model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.24.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.24.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.24.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.25.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.25.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.28.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.28.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.28.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.29.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.29.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.29.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.27.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"mtp.fc.weight": "model.safetensors-00003-of-00004.safetensors",
"mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.31.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00003-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.pos_embed.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.patch_embed.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.attn.proj.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.pre_fc_norm_embedding.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.pre_fc_norm_hidden.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.0.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.1.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.10.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.11.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.12.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.13.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.14.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.15.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.16.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.17.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.18.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.19.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.2.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.20.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.21.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.22.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.23.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.24.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.25.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.26.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.3.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.4.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.5.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.6.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.7.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.8.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.attn.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.norm1.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.norm1.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.norm2.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.blocks.9.norm2.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.norm.bias": "model.safetensors-00004-of-00004.safetensors",
"model.visual.merger.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.visual.patch_embed.proj.bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.27.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.31.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.26.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.30.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.24.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.25.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.28.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.29.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors",
"model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00004-of-00004.safetensors"
}
}

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"
}

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

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": 469762048,
"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",
"video_processor_type": "Qwen3VLVideoProcessor"
}

248046
vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff