Upload qwen3_vl_finetuned_base_classifier classifier
Browse files- .gitattributes +1 -0
- README.md +84 -0
- added_tokens.json +28 -0
- chat_template.jinja +120 -0
- config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +723 -0
- preprocessor_config.json +39 -0
- requirements.txt +5 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +666 -0
- training_args.bin +3 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA
|
| 4 |
+
tags:
|
| 5 |
+
- vision
|
| 6 |
+
- image-classification
|
| 7 |
+
- flowers
|
| 8 |
+
- multimodal
|
| 9 |
+
- qwen3-vl
|
| 10 |
+
- fine-tuned
|
| 11 |
+
datasets:
|
| 12 |
+
- flowers102
|
| 13 |
+
language:
|
| 14 |
+
- en
|
| 15 |
+
pipeline_tag: image-classification
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# Qwen3-VL Flowers102 Classifier
|
| 19 |
+
|
| 20 |
+
Qwen3-VL classifier trained on Flowers102 dataset using the fine-tuned oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA model. This model adds a classification head for 102 flower categories on top of an already fine-tuned base model.
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA](oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA) for flower classification on the Flowers102 dataset.
|
| 23 |
+
|
| 24 |
+
## Model Description
|
| 25 |
+
|
| 26 |
+
This is a multimodal classifier that combines:
|
| 27 |
+
- **Vision Encoder**: Qwen3-VL vision transformer
|
| 28 |
+
- **Language Model**: Qwen3-VL language model
|
| 29 |
+
- **Classification Head**: Custom linear layers for 102 flower classes
|
| 30 |
+
|
| 31 |
+
The model takes both image and text inputs (questions about flowers) and outputs classification predictions.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
## Usage
|
| 38 |
+
|
| 39 |
+
```python
|
| 40 |
+
from transformers import AutoProcessor
|
| 41 |
+
from src.models.qwen_classifier import Qwen3VLClassifier
|
| 42 |
+
import torch
|
| 43 |
+
from PIL import Image
|
| 44 |
+
|
| 45 |
+
# Load model and processor
|
| 46 |
+
model = Qwen3VLClassifier.from_pretrained("your-username/model-name")
|
| 47 |
+
processor = AutoProcessor.from_pretrained("oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA")
|
| 48 |
+
|
| 49 |
+
# Prepare inputs
|
| 50 |
+
image = Image.open("flower.jpg")
|
| 51 |
+
text = "What type of flower is this?"
|
| 52 |
+
|
| 53 |
+
# Create chat format
|
| 54 |
+
messages = [{
|
| 55 |
+
'role': 'user',
|
| 56 |
+
'content': [
|
| 57 |
+
{'type': 'image', 'image': image},
|
| 58 |
+
{'type': 'text', 'text': text}
|
| 59 |
+
]
|
| 60 |
+
}]
|
| 61 |
+
|
| 62 |
+
# Process inputs
|
| 63 |
+
text_input = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
|
| 64 |
+
inputs = processor(text=[text_input], images=[image], return_tensors="pt", padding=True)
|
| 65 |
+
|
| 66 |
+
# Get predictions
|
| 67 |
+
with torch.no_grad():
|
| 68 |
+
outputs = model(**inputs)
|
| 69 |
+
predicted_class = outputs.logits.argmax(dim=-1).item()
|
| 70 |
+
confidence = torch.softmax(outputs.logits, dim=-1).max().item()
|
| 71 |
+
|
| 72 |
+
print(f"Predicted class: {predicted_class}, Confidence: {confidence:.4f}")
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
## Dataset
|
| 76 |
+
|
| 77 |
+
The model was trained on the Flowers102 dataset, which contains 102 flower categories with:
|
| 78 |
+
- 7,169 training images
|
| 79 |
+
- 1,020 validation images
|
| 80 |
+
- 6,149 test images
|
| 81 |
+
|
| 82 |
+
## Citation
|
| 83 |
+
|
| 84 |
+
If you use this model, please cite the original Qwen3-VL paper and the Flowers102 dataset.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLClassifier"
|
| 4 |
+
],
|
| 5 |
+
"base_model_name_or_path": "oscarqjh/Qwen3-VL-4B-Instruct-Flowers102-Open-QA",
|
| 6 |
+
"dropout_rate": 0.1,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"freeze_base_model": true,
|
| 9 |
+
"model_type": "qwen3_vl_classifier",
|
| 10 |
+
"num_classes": 102,
|
| 11 |
+
"transformers_version": "4.57.1"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9c1df63b207a9d05bd33cc61fd88d102029936548417c3fd3eaee08733bf409
|
| 3 |
+
size 4990502384
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f74e6b39f2a5ba4c1f19b52b80e6ee13ef2bae46671217b1f5ac2d9c73728cf
|
| 3 |
+
size 3885745980
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4438077030,
|
| 4 |
+
"total_size": 8876154060
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"classifier.1.bias": "model-00002-of-00002.safetensors",
|
| 8 |
+
"classifier.1.weight": "model-00002-of-00002.safetensors",
|
| 9 |
+
"qwen3_vl.model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"qwen3_vl.model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"qwen3_vl.model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"qwen3_vl.model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"qwen3_vl.model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"qwen3_vl.model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"qwen3_vl.model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"qwen3_vl.model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"qwen3_vl.model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"qwen3_vl.model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"qwen3_vl.model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"qwen3_vl.model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"qwen3_vl.model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"qwen3_vl.model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"qwen3_vl.model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"qwen3_vl.model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"qwen3_vl.model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"qwen3_vl.model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"qwen3_vl.model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"qwen3_vl.model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"qwen3_vl.model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"qwen3_vl.model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"qwen3_vl.model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"qwen3_vl.model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"qwen3_vl.model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"qwen3_vl.model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"qwen3_vl.model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"qwen3_vl.model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"qwen3_vl.model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"qwen3_vl.model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"qwen3_vl.model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"qwen3_vl.model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"qwen3_vl.model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"qwen3_vl.model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"qwen3_vl.model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"qwen3_vl.model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"qwen3_vl.model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"qwen3_vl.model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"qwen3_vl.model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"qwen3_vl.model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"qwen3_vl.model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"qwen3_vl.model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"qwen3_vl.model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"qwen3_vl.model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"qwen3_vl.model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"qwen3_vl.model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"qwen3_vl.model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"qwen3_vl.model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"qwen3_vl.model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"qwen3_vl.model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"qwen3_vl.model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"qwen3_vl.model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"qwen3_vl.model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"qwen3_vl.model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 103 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"qwen3_vl.model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"qwen3_vl.model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"qwen3_vl.model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"qwen3_vl.model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"qwen3_vl.model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"qwen3_vl.model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"qwen3_vl.model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"qwen3_vl.model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"qwen3_vl.model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"qwen3_vl.model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"qwen3_vl.model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"qwen3_vl.model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"qwen3_vl.model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"qwen3_vl.model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"qwen3_vl.model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"qwen3_vl.model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"qwen3_vl.model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"qwen3_vl.model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"qwen3_vl.model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"qwen3_vl.model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"qwen3_vl.model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"qwen3_vl.model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"qwen3_vl.model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"qwen3_vl.model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"qwen3_vl.model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"qwen3_vl.model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"qwen3_vl.model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"qwen3_vl.model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"qwen3_vl.model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"qwen3_vl.model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"qwen3_vl.model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"qwen3_vl.model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"qwen3_vl.model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"qwen3_vl.model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"qwen3_vl.model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"qwen3_vl.model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"qwen3_vl.model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"qwen3_vl.model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"qwen3_vl.model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"qwen3_vl.model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"qwen3_vl.model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"qwen3_vl.model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"qwen3_vl.model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"qwen3_vl.model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"qwen3_vl.model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"qwen3_vl.model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"qwen3_vl.model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"qwen3_vl.model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"qwen3_vl.model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"qwen3_vl.model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"qwen3_vl.model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"qwen3_vl.model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"qwen3_vl.model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"qwen3_vl.model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"qwen3_vl.model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"qwen3_vl.model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"qwen3_vl.model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"qwen3_vl.model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"qwen3_vl.model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"qwen3_vl.model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"qwen3_vl.model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"qwen3_vl.model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"qwen3_vl.model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"qwen3_vl.model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"qwen3_vl.model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"qwen3_vl.model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"qwen3_vl.model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"qwen3_vl.model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"qwen3_vl.model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"qwen3_vl.model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"qwen3_vl.model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"qwen3_vl.model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"qwen3_vl.model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"qwen3_vl.model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"qwen3_vl.model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"qwen3_vl.model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"qwen3_vl.model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"qwen3_vl.model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"qwen3_vl.model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"qwen3_vl.model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"qwen3_vl.model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"qwen3_vl.model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"qwen3_vl.model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"qwen3_vl.model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"qwen3_vl.model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"qwen3_vl.model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"qwen3_vl.model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"qwen3_vl.model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"qwen3_vl.model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"qwen3_vl.model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"qwen3_vl.model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"qwen3_vl.model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"qwen3_vl.model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"qwen3_vl.model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"qwen3_vl.model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"qwen3_vl.model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"qwen3_vl.model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"qwen3_vl.model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"qwen3_vl.model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"qwen3_vl.model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"qwen3_vl.model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"qwen3_vl.model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"qwen3_vl.model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"qwen3_vl.model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"qwen3_vl.model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"qwen3_vl.model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"qwen3_vl.model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"qwen3_vl.model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"qwen3_vl.model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"qwen3_vl.model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"qwen3_vl.model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"qwen3_vl.model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"qwen3_vl.model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"qwen3_vl.model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"qwen3_vl.model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"qwen3_vl.model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"qwen3_vl.model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"qwen3_vl.model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"qwen3_vl.model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"qwen3_vl.model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"qwen3_vl.model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"qwen3_vl.model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"qwen3_vl.model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"qwen3_vl.model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"qwen3_vl.model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"qwen3_vl.model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"qwen3_vl.model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"qwen3_vl.model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"qwen3_vl.model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"qwen3_vl.model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"qwen3_vl.model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"qwen3_vl.model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"qwen3_vl.model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"qwen3_vl.model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"qwen3_vl.model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"qwen3_vl.model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"qwen3_vl.model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"qwen3_vl.model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"qwen3_vl.model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"qwen3_vl.model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"qwen3_vl.model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"qwen3_vl.model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"qwen3_vl.model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"qwen3_vl.model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"qwen3_vl.model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"qwen3_vl.model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"qwen3_vl.model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"qwen3_vl.model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"qwen3_vl.model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"qwen3_vl.model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"qwen3_vl.model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"qwen3_vl.model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"qwen3_vl.model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"qwen3_vl.model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"qwen3_vl.model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"qwen3_vl.model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"qwen3_vl.model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"qwen3_vl.model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"qwen3_vl.model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"qwen3_vl.model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"qwen3_vl.model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"qwen3_vl.model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"qwen3_vl.model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"qwen3_vl.model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"qwen3_vl.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"qwen3_vl.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"qwen3_vl.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"qwen3_vl.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"qwen3_vl.model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"qwen3_vl.model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"qwen3_vl.model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"qwen3_vl.model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"qwen3_vl.model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"qwen3_vl.model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"qwen3_vl.model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"qwen3_vl.model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"qwen3_vl.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"qwen3_vl.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"qwen3_vl.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"qwen3_vl.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"qwen3_vl.model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"qwen3_vl.model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"qwen3_vl.model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"qwen3_vl.model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"qwen3_vl.model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"qwen3_vl.model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"qwen3_vl.model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"qwen3_vl.model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"qwen3_vl.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"qwen3_vl.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"qwen3_vl.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"qwen3_vl.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"qwen3_vl.model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"qwen3_vl.model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"qwen3_vl.model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"qwen3_vl.model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"qwen3_vl.model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"qwen3_vl.model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"qwen3_vl.model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"qwen3_vl.model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"qwen3_vl.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"qwen3_vl.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"qwen3_vl.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"qwen3_vl.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"qwen3_vl.model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"qwen3_vl.model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"qwen3_vl.model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"qwen3_vl.model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"qwen3_vl.model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"qwen3_vl.model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"qwen3_vl.model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"qwen3_vl.model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"qwen3_vl.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"qwen3_vl.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"qwen3_vl.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"qwen3_vl.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"qwen3_vl.model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"qwen3_vl.model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"qwen3_vl.model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"qwen3_vl.model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"qwen3_vl.model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"qwen3_vl.model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"qwen3_vl.model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"qwen3_vl.model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"qwen3_vl.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"qwen3_vl.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"qwen3_vl.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"qwen3_vl.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"qwen3_vl.model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"qwen3_vl.model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"qwen3_vl.model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"qwen3_vl.model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"qwen3_vl.model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"qwen3_vl.model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"qwen3_vl.model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"qwen3_vl.model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"qwen3_vl.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"qwen3_vl.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"qwen3_vl.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"qwen3_vl.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"qwen3_vl.model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"qwen3_vl.model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"qwen3_vl.model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"qwen3_vl.model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"qwen3_vl.model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"qwen3_vl.model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"qwen3_vl.model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"qwen3_vl.model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"qwen3_vl.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"qwen3_vl.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"qwen3_vl.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"qwen3_vl.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"qwen3_vl.model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"qwen3_vl.model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"qwen3_vl.model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"qwen3_vl.model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"qwen3_vl.model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 500 |
+
"qwen3_vl.model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"qwen3_vl.model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"qwen3_vl.model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"qwen3_vl.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"qwen3_vl.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"qwen3_vl.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"qwen3_vl.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"qwen3_vl.model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 508 |
+
"qwen3_vl.model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"qwen3_vl.model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"qwen3_vl.model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"qwen3_vl.model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 512 |
+
"qwen3_vl.model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"qwen3_vl.model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"qwen3_vl.model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"qwen3_vl.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"qwen3_vl.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"qwen3_vl.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"qwen3_vl.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"qwen3_vl.model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"qwen3_vl.model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"qwen3_vl.model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"qwen3_vl.model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"qwen3_vl.model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"qwen3_vl.model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"qwen3_vl.model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"qwen3_vl.model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"qwen3_vl.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"qwen3_vl.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"qwen3_vl.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"qwen3_vl.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"qwen3_vl.model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"qwen3_vl.model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"qwen3_vl.model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"qwen3_vl.model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"qwen3_vl.model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 536 |
+
"qwen3_vl.model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"qwen3_vl.model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"qwen3_vl.model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"qwen3_vl.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"qwen3_vl.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"qwen3_vl.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"qwen3_vl.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"qwen3_vl.model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"qwen3_vl.model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"qwen3_vl.model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"qwen3_vl.model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"qwen3_vl.model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 548 |
+
"qwen3_vl.model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"qwen3_vl.model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"qwen3_vl.model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"qwen3_vl.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"qwen3_vl.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"qwen3_vl.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"qwen3_vl.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"qwen3_vl.model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"qwen3_vl.model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"qwen3_vl.model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"qwen3_vl.model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"qwen3_vl.model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 560 |
+
"qwen3_vl.model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"qwen3_vl.model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"qwen3_vl.model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"qwen3_vl.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"qwen3_vl.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"qwen3_vl.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"qwen3_vl.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"qwen3_vl.model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 568 |
+
"qwen3_vl.model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"qwen3_vl.model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"qwen3_vl.model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"qwen3_vl.model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 572 |
+
"qwen3_vl.model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"qwen3_vl.model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"qwen3_vl.model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"qwen3_vl.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"qwen3_vl.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"qwen3_vl.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"qwen3_vl.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"qwen3_vl.model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 580 |
+
"qwen3_vl.model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"qwen3_vl.model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"qwen3_vl.model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"qwen3_vl.model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 584 |
+
"qwen3_vl.model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"qwen3_vl.model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"qwen3_vl.model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"qwen3_vl.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"qwen3_vl.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"qwen3_vl.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"qwen3_vl.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"qwen3_vl.model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 592 |
+
"qwen3_vl.model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"qwen3_vl.model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"qwen3_vl.model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"qwen3_vl.model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 596 |
+
"qwen3_vl.model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"qwen3_vl.model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"qwen3_vl.model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"qwen3_vl.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"qwen3_vl.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"qwen3_vl.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"qwen3_vl.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"qwen3_vl.model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"qwen3_vl.model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"qwen3_vl.model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"qwen3_vl.model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"qwen3_vl.model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 608 |
+
"qwen3_vl.model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"qwen3_vl.model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"qwen3_vl.model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"qwen3_vl.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"qwen3_vl.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"qwen3_vl.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"qwen3_vl.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"qwen3_vl.model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"qwen3_vl.model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"qwen3_vl.model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"qwen3_vl.model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"qwen3_vl.model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 620 |
+
"qwen3_vl.model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"qwen3_vl.model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"qwen3_vl.model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"qwen3_vl.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"qwen3_vl.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"qwen3_vl.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"qwen3_vl.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"qwen3_vl.model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"qwen3_vl.model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"qwen3_vl.model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 630 |
+
"qwen3_vl.model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"qwen3_vl.model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 632 |
+
"qwen3_vl.model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"qwen3_vl.model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"qwen3_vl.model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"qwen3_vl.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 636 |
+
"qwen3_vl.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"qwen3_vl.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"qwen3_vl.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"qwen3_vl.model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 640 |
+
"qwen3_vl.model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"qwen3_vl.model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"qwen3_vl.model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"qwen3_vl.model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 644 |
+
"qwen3_vl.model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"qwen3_vl.model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"qwen3_vl.model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"qwen3_vl.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 648 |
+
"qwen3_vl.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"qwen3_vl.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 650 |
+
"qwen3_vl.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"qwen3_vl.model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"qwen3_vl.model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"qwen3_vl.model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"qwen3_vl.model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"qwen3_vl.model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"qwen3_vl.model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"qwen3_vl.model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"qwen3_vl.model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"qwen3_vl.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"qwen3_vl.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"qwen3_vl.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"qwen3_vl.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"qwen3_vl.model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"qwen3_vl.model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"qwen3_vl.model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"qwen3_vl.model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"qwen3_vl.model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"qwen3_vl.model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"qwen3_vl.model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"qwen3_vl.model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"qwen3_vl.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"qwen3_vl.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"qwen3_vl.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"qwen3_vl.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"qwen3_vl.model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"qwen3_vl.model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"qwen3_vl.model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"qwen3_vl.model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"qwen3_vl.model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 680 |
+
"qwen3_vl.model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"qwen3_vl.model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"qwen3_vl.model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"qwen3_vl.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"qwen3_vl.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"qwen3_vl.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"qwen3_vl.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"qwen3_vl.model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"qwen3_vl.model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"qwen3_vl.model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"qwen3_vl.model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"qwen3_vl.model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 692 |
+
"qwen3_vl.model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"qwen3_vl.model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"qwen3_vl.model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"qwen3_vl.model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 704 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"qwen3_vl.model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"qwen3_vl.model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"qwen3_vl.model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"qwen3_vl.model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"qwen3_vl.model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 716 |
+
"qwen3_vl.model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"qwen3_vl.model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"qwen3_vl.model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"qwen3_vl.model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"qwen3_vl.model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"qwen3_vl.model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
|
| 722 |
+
}
|
| 723 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch>=2.0.0
|
| 2 |
+
transformers>=4.40.0
|
| 3 |
+
Pillow
|
| 4 |
+
torchvision
|
| 5 |
+
accelerate
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 897,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011154489682097044,
|
| 14 |
+
"grad_norm": 808.0,
|
| 15 |
+
"learning_rate": 2e-05,
|
| 16 |
+
"loss": 107.6756,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.022308979364194088,
|
| 21 |
+
"grad_norm": 980.0,
|
| 22 |
+
"learning_rate": 4.222222222222222e-05,
|
| 23 |
+
"loss": 120.957,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03346346904629113,
|
| 28 |
+
"grad_norm": 956.0,
|
| 29 |
+
"learning_rate": 6.444444444444446e-05,
|
| 30 |
+
"loss": 112.0625,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.044617958728388175,
|
| 35 |
+
"grad_norm": 528.0,
|
| 36 |
+
"learning_rate": 8.666666666666667e-05,
|
| 37 |
+
"loss": 99.8676,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05577244841048522,
|
| 42 |
+
"grad_norm": 624.0,
|
| 43 |
+
"learning_rate": 0.00010888888888888889,
|
| 44 |
+
"loss": 81.8344,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06692693809258227,
|
| 49 |
+
"grad_norm": 516.0,
|
| 50 |
+
"learning_rate": 0.00013111111111111111,
|
| 51 |
+
"loss": 71.5164,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0780814277746793,
|
| 56 |
+
"grad_norm": 568.0,
|
| 57 |
+
"learning_rate": 0.00015333333333333334,
|
| 58 |
+
"loss": 54.2641,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08923591745677635,
|
| 63 |
+
"grad_norm": 548.0,
|
| 64 |
+
"learning_rate": 0.00017555555555555556,
|
| 65 |
+
"loss": 55.875,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1003904071388734,
|
| 70 |
+
"grad_norm": 556.0,
|
| 71 |
+
"learning_rate": 0.00019777777777777778,
|
| 72 |
+
"loss": 51.6243,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11154489682097044,
|
| 77 |
+
"grad_norm": 470.0,
|
| 78 |
+
"learning_rate": 0.00019776951672862453,
|
| 79 |
+
"loss": 40.6197,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.12269938650306748,
|
| 84 |
+
"grad_norm": 528.0,
|
| 85 |
+
"learning_rate": 0.0001952912019826518,
|
| 86 |
+
"loss": 45.5641,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13385387618516453,
|
| 91 |
+
"grad_norm": 398.0,
|
| 92 |
+
"learning_rate": 0.0001928128872366791,
|
| 93 |
+
"loss": 42.097,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.14500836586726157,
|
| 98 |
+
"grad_norm": 516.0,
|
| 99 |
+
"learning_rate": 0.00019033457249070633,
|
| 100 |
+
"loss": 40.4828,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1561628555493586,
|
| 105 |
+
"grad_norm": 496.0,
|
| 106 |
+
"learning_rate": 0.0001878562577447336,
|
| 107 |
+
"loss": 42.0313,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.16731734523145567,
|
| 112 |
+
"grad_norm": 470.0,
|
| 113 |
+
"learning_rate": 0.00018537794299876086,
|
| 114 |
+
"loss": 36.9686,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1784718349135527,
|
| 119 |
+
"grad_norm": 382.0,
|
| 120 |
+
"learning_rate": 0.0001828996282527881,
|
| 121 |
+
"loss": 32.9125,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.18962632459564974,
|
| 126 |
+
"grad_norm": 616.0,
|
| 127 |
+
"learning_rate": 0.00018042131350681537,
|
| 128 |
+
"loss": 36.5671,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2007808142777468,
|
| 133 |
+
"grad_norm": 556.0,
|
| 134 |
+
"learning_rate": 0.00017794299876084264,
|
| 135 |
+
"loss": 28.4831,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.21193530395984383,
|
| 140 |
+
"grad_norm": 492.0,
|
| 141 |
+
"learning_rate": 0.0001754646840148699,
|
| 142 |
+
"loss": 29.2506,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.22308979364194087,
|
| 147 |
+
"grad_norm": 508.0,
|
| 148 |
+
"learning_rate": 0.00017298636926889714,
|
| 149 |
+
"loss": 28.3438,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.23424428332403793,
|
| 154 |
+
"grad_norm": 520.0,
|
| 155 |
+
"learning_rate": 0.0001705080545229244,
|
| 156 |
+
"loss": 24.301,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.24539877300613497,
|
| 161 |
+
"grad_norm": 476.0,
|
| 162 |
+
"learning_rate": 0.00016802973977695168,
|
| 163 |
+
"loss": 25.7563,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.25655326268823203,
|
| 168 |
+
"grad_norm": 436.0,
|
| 169 |
+
"learning_rate": 0.00016555142503097895,
|
| 170 |
+
"loss": 24.0442,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.26770775237032907,
|
| 175 |
+
"grad_norm": 502.0,
|
| 176 |
+
"learning_rate": 0.00016307311028500621,
|
| 177 |
+
"loss": 20.3451,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2788622420524261,
|
| 182 |
+
"grad_norm": 384.0,
|
| 183 |
+
"learning_rate": 0.00016059479553903348,
|
| 184 |
+
"loss": 22.2586,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.29001673173452314,
|
| 189 |
+
"grad_norm": 474.0,
|
| 190 |
+
"learning_rate": 0.00015811648079306072,
|
| 191 |
+
"loss": 23.1332,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.30117122141662017,
|
| 196 |
+
"grad_norm": 568.0,
|
| 197 |
+
"learning_rate": 0.000155638166047088,
|
| 198 |
+
"loss": 19.4339,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3123257110987172,
|
| 203 |
+
"grad_norm": 464.0,
|
| 204 |
+
"learning_rate": 0.00015315985130111526,
|
| 205 |
+
"loss": 19.7892,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3234802007808143,
|
| 210 |
+
"grad_norm": 458.0,
|
| 211 |
+
"learning_rate": 0.0001506815365551425,
|
| 212 |
+
"loss": 21.4668,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.33463469046291133,
|
| 217 |
+
"grad_norm": 394.0,
|
| 218 |
+
"learning_rate": 0.00014820322180916976,
|
| 219 |
+
"loss": 17.7263,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.34578918014500837,
|
| 224 |
+
"grad_norm": 384.0,
|
| 225 |
+
"learning_rate": 0.00014572490706319703,
|
| 226 |
+
"loss": 16.1147,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3569436698271054,
|
| 231 |
+
"grad_norm": 498.0,
|
| 232 |
+
"learning_rate": 0.0001432465923172243,
|
| 233 |
+
"loss": 17.4189,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.36809815950920244,
|
| 238 |
+
"grad_norm": 424.0,
|
| 239 |
+
"learning_rate": 0.00014076827757125154,
|
| 240 |
+
"loss": 15.22,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3792526491912995,
|
| 245 |
+
"grad_norm": 408.0,
|
| 246 |
+
"learning_rate": 0.0001382899628252788,
|
| 247 |
+
"loss": 16.3009,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.39040713887339656,
|
| 252 |
+
"grad_norm": 422.0,
|
| 253 |
+
"learning_rate": 0.0001358116480793061,
|
| 254 |
+
"loss": 16.6557,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4015616285554936,
|
| 259 |
+
"grad_norm": 418.0,
|
| 260 |
+
"learning_rate": 0.00013333333333333334,
|
| 261 |
+
"loss": 14.89,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.41271611823759063,
|
| 266 |
+
"grad_norm": 330.0,
|
| 267 |
+
"learning_rate": 0.0001308550185873606,
|
| 268 |
+
"loss": 12.7717,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.42387060791968767,
|
| 273 |
+
"grad_norm": 502.0,
|
| 274 |
+
"learning_rate": 0.00012837670384138787,
|
| 275 |
+
"loss": 14.2706,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4350250976017847,
|
| 280 |
+
"grad_norm": 432.0,
|
| 281 |
+
"learning_rate": 0.00012589838909541511,
|
| 282 |
+
"loss": 15.7935,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.44617958728388174,
|
| 287 |
+
"grad_norm": 454.0,
|
| 288 |
+
"learning_rate": 0.00012342007434944238,
|
| 289 |
+
"loss": 14.2595,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.45733407696597883,
|
| 294 |
+
"grad_norm": 243.0,
|
| 295 |
+
"learning_rate": 0.00012094175960346965,
|
| 296 |
+
"loss": 12.5059,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.46848856664807587,
|
| 301 |
+
"grad_norm": 400.0,
|
| 302 |
+
"learning_rate": 0.0001184634448574969,
|
| 303 |
+
"loss": 13.2633,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4796430563301729,
|
| 308 |
+
"grad_norm": 378.0,
|
| 309 |
+
"learning_rate": 0.00011598513011152417,
|
| 310 |
+
"loss": 10.6085,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.49079754601226994,
|
| 315 |
+
"grad_norm": 288.0,
|
| 316 |
+
"learning_rate": 0.00011350681536555144,
|
| 317 |
+
"loss": 13.1564,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.501952035694367,
|
| 322 |
+
"grad_norm": 402.0,
|
| 323 |
+
"learning_rate": 0.0001110285006195787,
|
| 324 |
+
"loss": 11.3698,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5131065253764641,
|
| 329 |
+
"grad_norm": 292.0,
|
| 330 |
+
"learning_rate": 0.00010855018587360594,
|
| 331 |
+
"loss": 10.3364,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.524261015058561,
|
| 336 |
+
"grad_norm": 370.0,
|
| 337 |
+
"learning_rate": 0.00010607187112763321,
|
| 338 |
+
"loss": 11.7727,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5354155047406581,
|
| 343 |
+
"grad_norm": 416.0,
|
| 344 |
+
"learning_rate": 0.00010359355638166048,
|
| 345 |
+
"loss": 10.1074,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5465699944227551,
|
| 350 |
+
"grad_norm": 442.0,
|
| 351 |
+
"learning_rate": 0.00010111524163568773,
|
| 352 |
+
"loss": 12.4912,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5577244841048522,
|
| 357 |
+
"grad_norm": 278.0,
|
| 358 |
+
"learning_rate": 9.8636926889715e-05,
|
| 359 |
+
"loss": 10.6493,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5688789737869493,
|
| 364 |
+
"grad_norm": 324.0,
|
| 365 |
+
"learning_rate": 9.615861214374225e-05,
|
| 366 |
+
"loss": 10.2889,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5800334634690463,
|
| 371 |
+
"grad_norm": 410.0,
|
| 372 |
+
"learning_rate": 9.368029739776952e-05,
|
| 373 |
+
"loss": 11.2218,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5911879531511434,
|
| 378 |
+
"grad_norm": 318.0,
|
| 379 |
+
"learning_rate": 9.120198265179678e-05,
|
| 380 |
+
"loss": 9.0832,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6023424428332403,
|
| 385 |
+
"grad_norm": 378.0,
|
| 386 |
+
"learning_rate": 8.872366790582404e-05,
|
| 387 |
+
"loss": 9.1207,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6134969325153374,
|
| 392 |
+
"grad_norm": 296.0,
|
| 393 |
+
"learning_rate": 8.624535315985131e-05,
|
| 394 |
+
"loss": 9.3185,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6246514221974344,
|
| 399 |
+
"grad_norm": 256.0,
|
| 400 |
+
"learning_rate": 8.376703841387856e-05,
|
| 401 |
+
"loss": 7.045,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6358059118795315,
|
| 406 |
+
"grad_norm": 276.0,
|
| 407 |
+
"learning_rate": 8.128872366790583e-05,
|
| 408 |
+
"loss": 9.9175,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6469604015616286,
|
| 413 |
+
"grad_norm": 358.0,
|
| 414 |
+
"learning_rate": 7.881040892193308e-05,
|
| 415 |
+
"loss": 9.9291,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6581148912437256,
|
| 420 |
+
"grad_norm": 290.0,
|
| 421 |
+
"learning_rate": 7.633209417596035e-05,
|
| 422 |
+
"loss": 11.4162,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6692693809258227,
|
| 427 |
+
"grad_norm": 334.0,
|
| 428 |
+
"learning_rate": 7.385377942998762e-05,
|
| 429 |
+
"loss": 10.3434,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6804238706079196,
|
| 434 |
+
"grad_norm": 272.0,
|
| 435 |
+
"learning_rate": 7.137546468401487e-05,
|
| 436 |
+
"loss": 8.3913,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6915783602900167,
|
| 441 |
+
"grad_norm": 360.0,
|
| 442 |
+
"learning_rate": 6.889714993804214e-05,
|
| 443 |
+
"loss": 8.3737,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7027328499721138,
|
| 448 |
+
"grad_norm": 328.0,
|
| 449 |
+
"learning_rate": 6.64188351920694e-05,
|
| 450 |
+
"loss": 9.3919,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7138873396542108,
|
| 455 |
+
"grad_norm": 568.0,
|
| 456 |
+
"learning_rate": 6.394052044609665e-05,
|
| 457 |
+
"loss": 10.5123,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7250418293363079,
|
| 462 |
+
"grad_norm": 302.0,
|
| 463 |
+
"learning_rate": 6.146220570012391e-05,
|
| 464 |
+
"loss": 9.4829,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7361963190184049,
|
| 469 |
+
"grad_norm": 380.0,
|
| 470 |
+
"learning_rate": 5.8983890954151175e-05,
|
| 471 |
+
"loss": 8.2973,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.747350808700502,
|
| 476 |
+
"grad_norm": 332.0,
|
| 477 |
+
"learning_rate": 5.650557620817844e-05,
|
| 478 |
+
"loss": 7.8408,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.758505298382599,
|
| 483 |
+
"grad_norm": 201.0,
|
| 484 |
+
"learning_rate": 5.40272614622057e-05,
|
| 485 |
+
"loss": 7.4562,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.769659788064696,
|
| 490 |
+
"grad_norm": 360.0,
|
| 491 |
+
"learning_rate": 5.154894671623296e-05,
|
| 492 |
+
"loss": 8.5639,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7808142777467931,
|
| 497 |
+
"grad_norm": 366.0,
|
| 498 |
+
"learning_rate": 4.907063197026023e-05,
|
| 499 |
+
"loss": 8.5916,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7919687674288901,
|
| 504 |
+
"grad_norm": 364.0,
|
| 505 |
+
"learning_rate": 4.6592317224287485e-05,
|
| 506 |
+
"loss": 8.4457,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8031232571109872,
|
| 511 |
+
"grad_norm": 346.0,
|
| 512 |
+
"learning_rate": 4.4114002478314745e-05,
|
| 513 |
+
"loss": 8.609,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8142777467930842,
|
| 518 |
+
"grad_norm": 280.0,
|
| 519 |
+
"learning_rate": 4.163568773234201e-05,
|
| 520 |
+
"loss": 9.5489,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8254322364751813,
|
| 525 |
+
"grad_norm": 185.0,
|
| 526 |
+
"learning_rate": 3.915737298636927e-05,
|
| 527 |
+
"loss": 7.9562,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8365867261572784,
|
| 532 |
+
"grad_norm": 290.0,
|
| 533 |
+
"learning_rate": 3.667905824039653e-05,
|
| 534 |
+
"loss": 7.4137,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8477412158393753,
|
| 539 |
+
"grad_norm": 197.0,
|
| 540 |
+
"learning_rate": 3.4200743494423794e-05,
|
| 541 |
+
"loss": 9.2086,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8588957055214724,
|
| 546 |
+
"grad_norm": 253.0,
|
| 547 |
+
"learning_rate": 3.1722428748451055e-05,
|
| 548 |
+
"loss": 8.1385,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8700501952035694,
|
| 553 |
+
"grad_norm": 286.0,
|
| 554 |
+
"learning_rate": 2.924411400247832e-05,
|
| 555 |
+
"loss": 7.7596,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8812046848856665,
|
| 560 |
+
"grad_norm": 404.0,
|
| 561 |
+
"learning_rate": 2.6765799256505576e-05,
|
| 562 |
+
"loss": 8.1014,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8923591745677635,
|
| 567 |
+
"grad_norm": 284.0,
|
| 568 |
+
"learning_rate": 2.4287484510532836e-05,
|
| 569 |
+
"loss": 7.4541,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9035136642498606,
|
| 574 |
+
"grad_norm": 229.0,
|
| 575 |
+
"learning_rate": 2.18091697645601e-05,
|
| 576 |
+
"loss": 9.0809,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9146681539319577,
|
| 581 |
+
"grad_norm": 418.0,
|
| 582 |
+
"learning_rate": 1.9330855018587364e-05,
|
| 583 |
+
"loss": 9.1107,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9258226436140546,
|
| 588 |
+
"grad_norm": 370.0,
|
| 589 |
+
"learning_rate": 1.685254027261462e-05,
|
| 590 |
+
"loss": 9.5154,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9369771332961517,
|
| 595 |
+
"grad_norm": 376.0,
|
| 596 |
+
"learning_rate": 1.4374225526641885e-05,
|
| 597 |
+
"loss": 10.4265,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9481316229782487,
|
| 602 |
+
"grad_norm": 225.0,
|
| 603 |
+
"learning_rate": 1.1895910780669145e-05,
|
| 604 |
+
"loss": 8.4274,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9592861126603458,
|
| 609 |
+
"grad_norm": 478.0,
|
| 610 |
+
"learning_rate": 9.417596034696406e-06,
|
| 611 |
+
"loss": 8.4255,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9704406023424428,
|
| 616 |
+
"grad_norm": 344.0,
|
| 617 |
+
"learning_rate": 6.939281288723669e-06,
|
| 618 |
+
"loss": 7.6423,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9815950920245399,
|
| 623 |
+
"grad_norm": 358.0,
|
| 624 |
+
"learning_rate": 4.4609665427509296e-06,
|
| 625 |
+
"loss": 7.3096,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.992749581706637,
|
| 630 |
+
"grad_norm": 316.0,
|
| 631 |
+
"learning_rate": 1.982651796778191e-06,
|
| 632 |
+
"loss": 9.8214,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.0,
|
| 637 |
+
"step": 897,
|
| 638 |
+
"total_flos": 4.962997023381914e+16,
|
| 639 |
+
"train_loss": 22.294092814127605,
|
| 640 |
+
"train_runtime": 338.838,
|
| 641 |
+
"train_samples_per_second": 21.158,
|
| 642 |
+
"train_steps_per_second": 2.647
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"logging_steps": 10,
|
| 646 |
+
"max_steps": 897,
|
| 647 |
+
"num_input_tokens_seen": 0,
|
| 648 |
+
"num_train_epochs": 1,
|
| 649 |
+
"save_steps": 100,
|
| 650 |
+
"stateful_callbacks": {
|
| 651 |
+
"TrainerControl": {
|
| 652 |
+
"args": {
|
| 653 |
+
"should_epoch_stop": false,
|
| 654 |
+
"should_evaluate": false,
|
| 655 |
+
"should_log": false,
|
| 656 |
+
"should_save": true,
|
| 657 |
+
"should_training_stop": true
|
| 658 |
+
},
|
| 659 |
+
"attributes": {}
|
| 660 |
+
}
|
| 661 |
+
},
|
| 662 |
+
"total_flos": 4.962997023381914e+16,
|
| 663 |
+
"train_batch_size": 1,
|
| 664 |
+
"trial_name": null,
|
| 665 |
+
"trial_params": null
|
| 666 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0adb6cbb88f46c1ec4c583c5c22925a1d2abddcb3e5bb295ca372bd2ed60fff
|
| 3 |
+
size 5905
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|