Upload 18 files
#3
by
maybleMyers
- opened
- .gitattributes +1 -0
- Qwen3-VL-8B-Caption-V4.5/.gitattributes +36 -0
- Qwen3-VL-8B-Caption-V4.5/README.md +119 -0
- Qwen3-VL-8B-Caption-V4.5/README_EN.md +130 -0
- Qwen3-VL-8B-Caption-V4.5/added_tokens.json +28 -0
- Qwen3-VL-8B-Caption-V4.5/chat_template.jinja +120 -0
- Qwen3-VL-8B-Caption-V4.5/config.json +66 -0
- Qwen3-VL-8B-Caption-V4.5/merges.txt +0 -0
- Qwen3-VL-8B-Caption-V4.5/model-00001-of-00004.safetensors +3 -0
- Qwen3-VL-8B-Caption-V4.5/model-00002-of-00004.safetensors +3 -0
- Qwen3-VL-8B-Caption-V4.5/model-00003-of-00004.safetensors +3 -0
- Qwen3-VL-8B-Caption-V4.5/model-00004-of-00004.safetensors +3 -0
- Qwen3-VL-8B-Caption-V4.5/model.safetensors.index.json +757 -0
- Qwen3-VL-8B-Caption-V4.5/preprocessor_config.json +39 -0
- Qwen3-VL-8B-Caption-V4.5/special_tokens_map.json +31 -0
- Qwen3-VL-8B-Caption-V4.5/tokenizer.json +3 -0
- Qwen3-VL-8B-Caption-V4.5/tokenizer_config.json +248 -0
- Qwen3-VL-8B-Caption-V4.5/video_preprocessor_config.json +41 -0
- Qwen3-VL-8B-Caption-V4.5/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 |
+
Qwen3-VL-8B-Caption-V4.5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Qwen3-VL-8B-Caption-V4.5/.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
Qwen3-VL-8B-Caption-V4.5/README.md
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- zh
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- qwen
|
| 8 |
+
- qwen3-vl
|
| 9 |
+
- image-captioning
|
| 10 |
+
- multimodal
|
| 11 |
+
- long-caption
|
| 12 |
+
library_name: transformers
|
| 13 |
+
base_model:
|
| 14 |
+
- Qwen/Qwen3-VL-8B-Instruct
|
| 15 |
+
---
|
| 16 |
+
[README_EN.md](https://huggingface.co/thesby/Qwen3-VL-8B-NSFW-Caption-V4.5/blob/main/README_EN.md)
|
| 17 |
+
# 模型名称：thesby/Qwen3-VL-8B-NSFW-Caption-V4.5
|
| 18 |
+
|
| 19 |
+
欢迎加入 [Discord](https://discord.gg/x7MzSZ3Y9) 进行友好交流。
|
| 20 |
+
|
| 21 |
+
## 模型简介 (Model Description)
|
| 22 |
+
|
| 23 |
+
**thesby/Qwen3-VL-8B-NSFW-Caption-V4.5** 是一个专为高质量图像描述（Image Captioning）而优化的多模态大模型。该模型基于强大的 `Qwen/Qwen3-VL-8B-Instruct` 进行Lora微调，旨在提供卓越的图像理解和描述生成能力。
|
| 24 |
+
|
| 25 |
+
我们在一个包含约 **200 万** 高质量图文对的混合数据集上对模型进行了训练，使其在多个维度上都表现出色。
|
| 26 |
+
|
| 27 |
+
### 主要更新(New Features)
|
| 28 |
+
1. **解决英文prompt拒绝描述图片的问题**：
|
| 29 |
+
2. **支持短视频描述**
|
| 30 |
+
|
| 31 |
+
### 主要特点 (Key Features)
|
| 32 |
+
|
| 33 |
+
1. **超高质量的图片描述能力 (Ultra-High Quality Captions)**：
|
| 34 |
+
模型能够精准捕捉图像中的核心主体、环境背景、人物情绪、物体材质和光影等丰富细节，描述能力超过 gpt4.1-mini，接近于 gemini-2.5-flash。
|
| 35 |
+
2. **SFW & NSFW 内容全覆盖 (Support for both SFW & NSFW Content)**：
|
| 36 |
+
经过特殊的数据集训练，模型能够有效识别并描述 SFW (Safe for Work) 和 NSFW (Not Safe for Work) 类型的图像内容。无论是日常生活场景还是成人向内容，都能生成恰当且信息丰富的描述，极大地拓宽了模型的适用边界。
|
| 37 |
+
3. **超长文本描述能力 (Long-form Detailed Description)**：
|
| 38 |
+
与传统模型生成简短标题不同，本模型擅长对复杂的图像场景进行详尽入微的描绘。它可以生成包含数百个单词的详细段落，深入分析图像的叙事结构和潜在含义，尤其适合需要深度内容解读的应用场景。
|
| 39 |
+
## 如何使用 (How to Use)
|
| 40 |
+
使用 vllm 可以获得更好的性能，请参考脚本：[get_vlm_caption.py](https://huggingface.co/thesby/Qwen2.5-VL-7B-NSFW-Caption-V4-W8A16/blob/main/get_vlm_caption.py)
|
| 41 |
+
|
| 42 |
+
transformers 使用方式和 Qwen/Qwen3-VL-8B-Instruct 完全相同，模型在图片最大尺寸 800*800 微调，遵从这一设置可以获得更好的效果。
|
| 43 |
+
```python
|
| 44 |
+
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
|
| 45 |
+
# default: Load the model on the available device(s)
|
| 46 |
+
model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 47 |
+
"thesby/Qwen3-VL-8B-NSFW-Caption-V4.5", dtype="auto", device_map="auto"
|
| 48 |
+
)
|
| 49 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
| 50 |
+
# model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 51 |
+
# "thesby/Qwen3-VL-8B-NSFW-Caption-V4.5",
|
| 52 |
+
# dtype=torch.bfloat16,
|
| 53 |
+
# attn_implementation="flash_attention_2",
|
| 54 |
+
# device_map="auto",
|
| 55 |
+
# )
|
| 56 |
+
processor = AutoProcessor.from_pretrained("thesby/Qwen3-VL-8B-NSFW-Caption-V4.5")
|
| 57 |
+
messages = [
|
| 58 |
+
{
|
| 59 |
+
"role": "user",
|
| 60 |
+
"content": [
|
| 61 |
+
{
|
| 62 |
+
"type": "image",
|
| 63 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 64 |
+
},
|
| 65 |
+
{"type": "text", "text": "请用自然流畅的中文对以下图片进行全面而详细的描述。包括所有可见元素及其属性（如颜色、大小、形状、质地），它们的空间关系，以及任何显著特征或上下文。确保用自然流畅的中文描述清晰、生动，能够捕捉图片的每一个方面，不遗漏任何重要细节。"},
|
| 66 |
+
],
|
| 67 |
+
}
|
| 68 |
+
]
|
| 69 |
+
# Preparation for inference
|
| 70 |
+
inputs = processor.apply_chat_template(
|
| 71 |
+
messages,
|
| 72 |
+
tokenize=True,
|
| 73 |
+
add_generation_prompt=True,
|
| 74 |
+
return_dict=True,
|
| 75 |
+
return_tensors="pt"
|
| 76 |
+
)
|
| 77 |
+
inputs = inputs.to(model.device)
|
| 78 |
+
# Inference: Generation of the output
|
| 79 |
+
generated_ids = model.generate(**inputs, max_new_tokens=2048)
|
| 80 |
+
generated_ids_trimmed = [
|
| 81 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 82 |
+
]
|
| 83 |
+
output_text = processor.batch_decode(
|
| 84 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 85 |
+
)
|
| 86 |
+
print(output_text)
|
| 87 |
+
```
|
| 88 |
+
|
| 89 |
+
视频只需要将按照 fps=1 抽帧作为图片放入 messages 即可。
|
| 90 |
+
|
| 91 |
+
## 用途与限制 (Uses and Limitations)
|
| 92 |
+
### 预期用途 (Intended Uses)
|
| 93 |
+
* **自动化内容标注**：为海量图片生成高质量的描述和标签，用于内容管理、检索和推荐系统。
|
| 94 |
+
* **无障碍辅助功能**：为视障用户描述图像内容，帮助他们理解视觉信息。
|
| 95 |
+
* **创意内容生成**：作为灵感来源，为艺术创作、故事写作、广告文案等提供基于图像的文本描述。
|
| 96 |
+
* **数字内容分析**：对包括SFW和NSFW在内的多种图像内容进行自动化分析和归档。
|
| 97 |
+
### 不适用范围 (Out-of-Scope)
|
| 98 |
+
* 本模型不应用于生成任何有害、非法、歧视性或侵犯他人隐私的内容。
|
| 99 |
+
* 模型的输出不应被视为绝对事实，更不能用于任何需要高精度和高可靠性的关键决策（如医疗诊断、法律判决等），所有重要应用都需有人工审核。
|
| 100 |
+
* 用户在使用模型处理NSFW内容时，应严格遵守当地法律法规，并承担相应责任。
|
| 101 |
+
### 局限性与偏见 (Limitations and Bias)
|
| 102 |
+
* **幻觉 (Hallucination)**：与所有大模型一样，本模型可能产生“幻觉”，即生成图像中不存在的细节。
|
| 103 |
+
* **数据偏见 (Data Bias)**：模型的输出可能反映其训练数据中存在的社会和文化偏见（例如，在性别、种族或年龄方面的刻板印象）。
|
| 104 |
+
* **NSFW判断边界**：对于处于SFW和NSFW边界的模糊图像，模型的判断和描述可能与人类预期不符。
|
| 105 |
+
## 训练细节 (Training Details)
|
| 106 |
+
### 训练数据 (Training Data)
|
| 107 |
+
本模型在一个精心构建的、约 **200 万** 图文对的数据集上进行了微调。该数据集经过严格的筛选和清洗，混合了：
|
| 108 |
+
* 高质量的公开图文数据集。
|
| 109 |
+
* 专门收集和标注的、涵盖广泛SFW和NSFW场景的私有数据集。
|
| 110 |
+
数据分布旨在提升模型在细节捕捉和长文本生成方面的能力，同时确保对不同类型内容的泛化性。
|
| 111 |
+
### 训练过程 (Training Procedure)
|
| 112 |
+
* **基础模型 (Base Model)**：`Qwen/Qwen3-VL-8B-Instruct`
|
| 113 |
+
* **微调策略 (Finetuning Strategy)**：Lora微调 (Lora Fine-tuning)
|
| 114 |
+
* **框架 (Framework)**：unsloth
|
| 115 |
+
|
| 116 |
+
### 计划 (Plans)
|
| 117 |
+
* 提高人物动作描述准确性
|
| 118 |
+
* 提高视频描述准确性
|
| 119 |
+
* 恢复Qwen3-VL通用视觉能力
|
Qwen3-VL-8B-Caption-V4.5/README_EN.md
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
---
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
language:
|
| 6 |
+
- zh
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- qwen
|
| 10 |
+
- qwen3-vl
|
| 11 |
+
- image-captioning
|
| 12 |
+
- multimodal
|
| 13 |
+
- long-caption
|
| 14 |
+
library_name: transformers
|
| 15 |
+
base_model:
|
| 16 |
+
- Qwen/Qwen3-VL-8B-Instruct
|
| 17 |
+
---
|
| 18 |
+
# Model Name: thesby/Qwen3-VL-8B-NSFW-Caption-V4.5
|
| 19 |
+
|
| 20 |
+
[discord](https://discord.gg/x7MzSZ3Y9)
|
| 21 |
+
|
| 22 |
+
## Model Description
|
| 23 |
+
|
| 24 |
+
**thesby/Qwen3-VL-8B-NSFW-Caption-V4.5** is a multimodal large model specifically optimized for high-quality image captioning. This model is fine-tuned using LoRA on the powerful `Qwen/Qwen3-VL-8B-Instruct`, aiming to provide exceptional image understanding and description generation capabilities.
|
| 25 |
+
|
| 26 |
+
We trained the model on a mixed dataset containing approximately **2 million** high-quality image-text pairs, enabling it to excel in multiple dimensions.
|
| 27 |
+
|
| 28 |
+
### New Features
|
| 29 |
+
1. **Resolved the issue of refusing to describe images when prompted in English**
|
| 30 |
+
2. **Support for short video descriptions**
|
| 31 |
+
|
| 32 |
+
### Key Features
|
| 33 |
+
|
| 34 |
+
1. **Ultra-High Quality Captions**:
|
| 35 |
+
The model can accurately capture core subjects, environmental backgrounds, character emotions, object materials, and lighting details in images. Its description capabilities surpass gpt4.1-mini and approach those of gemini-2.5-flash.
|
| 36 |
+
2. **Support for both SFW & NSFW Content**:
|
| 37 |
+
Trained on a special dataset, the model can effectively recognize and describe both SFW (Safe for Work) and NSFW (Not Safe for Work) image content. Whether it's everyday scenes or adult-oriented content, it can generate appropriate and information-rich descriptions, greatly expanding the model's application boundaries.
|
| 38 |
+
3. **Long-form Detailed Description**:
|
| 39 |
+
Unlike traditional models that generate short captions, this model excels at providing detailed and nuanced descriptions of complex image scenes. It can generate detailed paragraphs containing hundreds of words, deeply analyzing the narrative structure and potential meanings of images, making it particularly suitable for applications requiring deep content interpretation.
|
| 40 |
+
|
| 41 |
+
## How to Use
|
| 42 |
+
|
| 43 |
+
For better performance, we recommend using vllm. Please refer to the script: [get_vlm_caption.py](https://huggingface.co/thesby/Qwen2.5-VL-7B-NSFW-Caption-V4-W8A16/blob/main/get_vlm_caption.py)
|
| 44 |
+
|
| 45 |
+
The usage with transformers is identical to Qwen/Qwen3-VL-8B-Instruct. The model was fine-tuned with a maximum image size of 800*800, and following this setting will yield better results.
|
| 46 |
+
|
| 47 |
+
```python
|
| 48 |
+
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
|
| 49 |
+
# default: Load the model on the available device(s)
|
| 50 |
+
model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 51 |
+
"thesby/Qwen3-VL-8B-NSFW-Caption-V4.5", dtype="auto", device_map="auto"
|
| 52 |
+
)
|
| 53 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
| 54 |
+
# model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 55 |
+
# "thesby/Qwen3-VL-8B-NSFW-Caption-V4.5",
|
| 56 |
+
# dtype=torch.bfloat16,
|
| 57 |
+
# attn_implementation="flash_attention_2",
|
| 58 |
+
# device_map="auto",
|
| 59 |
+
# )
|
| 60 |
+
processor = AutoProcessor.from_pretrained("thesby/Qwen3-VL-8B-NSFW-Caption-V4.5")
|
| 61 |
+
messages = [
|
| 62 |
+
{
|
| 63 |
+
"role": "user",
|
| 64 |
+
"content": [
|
| 65 |
+
{
|
| 66 |
+
"type": "image",
|
| 67 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 68 |
+
},
|
| 69 |
+
{"type": "text", "text": "Describe the image in detail."},
|
| 70 |
+
],
|
| 71 |
+
}
|
| 72 |
+
]
|
| 73 |
+
# Preparation for inference
|
| 74 |
+
inputs = processor.apply_chat_template(
|
| 75 |
+
messages,
|
| 76 |
+
tokenize=True,
|
| 77 |
+
add_generation_prompt=True,
|
| 78 |
+
return_dict=True,
|
| 79 |
+
return_tensors="pt"
|
| 80 |
+
)
|
| 81 |
+
inputs = inputs.to(model.device)
|
| 82 |
+
# Inference: Generation of the output
|
| 83 |
+
generated_ids = model.generate(**inputs, max_new_tokens=2048)
|
| 84 |
+
generated_ids_trimmed = [
|
| 85 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 86 |
+
]
|
| 87 |
+
output_text = processor.batch_decode(
|
| 88 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 89 |
+
)
|
| 90 |
+
print(output_text)
|
| 91 |
+
```
|
| 92 |
+
|
| 93 |
+
For videos, simply extract frames at fps=1 and include them as images in the messages.
|
| 94 |
+
|
| 95 |
+
## Uses and Limitations
|
| 96 |
+
|
| 97 |
+
### Intended Uses
|
| 98 |
+
* **Automated Content Annotation**: Generate high-quality descriptions and tags for large volumes of images for content management, retrieval, and recommendation systems.
|
| 99 |
+
* **Accessibility Assistance**: Describe image content for visually impaired users to help them understand visual information.
|
| 100 |
+
* **Creative Content Generation**: Serve as a source of inspiration for artistic creation, story writing, advertising copy, etc., by providing text descriptions based on images.
|
| 101 |
+
* **Digital Content Analysis**: Automatically analyze and archive various image content, including both SFW and NSFW.
|
| 102 |
+
|
| 103 |
+
### Out-of-Scope
|
| 104 |
+
* This model should not be used to generate any harmful, illegal, discriminatory, or privacy-violating content.
|
| 105 |
+
* The model's output should not be considered absolute fact and should not be used for any critical decisions requiring high precision and reliability (such as medical diagnosis, legal judgments, etc.). All important applications require human review.
|
| 106 |
+
* When using the model to process NSFW content, users should strictly comply with local laws and regulations and assume corresponding responsibilities.
|
| 107 |
+
|
| 108 |
+
### Limitations and Bias
|
| 109 |
+
* **Hallucination**: Like all large models, this model may produce "hallucinations," i.e., generate details that do not exist in the image.
|
| 110 |
+
* **Data Bias**: The model's output may reflect social and cultural biases present in its training data (e.g., stereotypes regarding gender, race, or age).
|
| 111 |
+
* **NSFW Judgment Boundaries**: For ambiguous images at the boundary between SFW and NSFW, the model's judgment and description may not match human expectations.
|
| 112 |
+
|
| 113 |
+
## Training Details
|
| 114 |
+
|
| 115 |
+
### Training Data
|
| 116 |
+
This model was fine-tuned on a carefully constructed dataset of approximately **2 million** image-text pairs. This dataset underwent rigorous screening and cleaning, mixing:
|
| 117 |
+
* High-quality public image-text datasets.
|
| 118 |
+
* Privately collected and annotated datasets covering a wide range of SFW and NSFW scenarios.
|
| 119 |
+
|
| 120 |
+
The data distribution aims to enhance the model's capabilities in detail capture and long-text generation while ensuring generalization across different types of content.
|
| 121 |
+
|
| 122 |
+
### Training Procedure
|
| 123 |
+
* **Base Model**: `Qwen/Qwen3-VL-8B-Instruct`
|
| 124 |
+
* **Finetuning Strategy**: LoRA Fine-tuning
|
| 125 |
+
* **Framework**: unsloth
|
| 126 |
+
|
| 127 |
+
### Plans
|
| 128 |
+
* Improve accuracy of human action descriptions
|
| 129 |
+
* Improve accuracy of video descriptions
|
| 130 |
+
* Restore Qwen3-VL general vision capabilities
|
Qwen3-VL-8B-Caption-V4.5/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 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/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 %}
|
Qwen3-VL-8B-Caption-V4.5/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"torch_dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 151643,
|
| 13 |
+
"torch_dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 151645,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 4096,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 12288,
|
| 20 |
+
"max_position_embeddings": 262144,
|
| 21 |
+
"model_type": "qwen3_vl_text",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 36,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"mrope_interleaved": true,
|
| 28 |
+
"mrope_section": [
|
| 29 |
+
24,
|
| 30 |
+
20,
|
| 31 |
+
20
|
| 32 |
+
],
|
| 33 |
+
"rope_type": "default"
|
| 34 |
+
},
|
| 35 |
+
"rope_theta": 5000000,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 151936
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": false,
|
| 40 |
+
"transformers_version": "4.57.1",
|
| 41 |
+
"unsloth_version": "2025.11.1",
|
| 42 |
+
"video_token_id": 151656,
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"deepstack_visual_indexes": [
|
| 45 |
+
8,
|
| 46 |
+
16,
|
| 47 |
+
24
|
| 48 |
+
],
|
| 49 |
+
"depth": 27,
|
| 50 |
+
"torch_dtype": "bfloat16",
|
| 51 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 52 |
+
"hidden_size": 1152,
|
| 53 |
+
"in_channels": 3,
|
| 54 |
+
"initializer_range": 0.02,
|
| 55 |
+
"intermediate_size": 4304,
|
| 56 |
+
"model_type": "qwen3_vl",
|
| 57 |
+
"num_heads": 16,
|
| 58 |
+
"num_position_embeddings": 2304,
|
| 59 |
+
"out_hidden_size": 4096,
|
| 60 |
+
"patch_size": 16,
|
| 61 |
+
"spatial_merge_size": 2,
|
| 62 |
+
"temporal_patch_size": 2
|
| 63 |
+
},
|
| 64 |
+
"vision_end_token_id": 151653,
|
| 65 |
+
"vision_start_token_id": 151652
|
| 66 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen3-VL-8B-Caption-V4.5/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:987fe5e08feb7a9e98322b36dd036ced0fbed19a281e89ef8fd096d300ca072e
|
| 3 |
+
size 4902275944
|
Qwen3-VL-8B-Caption-V4.5/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f899cd22c3b17902f66712e10269cc36b986c15584df7478438ee8dd401375b7
|
| 3 |
+
size 4915962496
|
Qwen3-VL-8B-Caption-V4.5/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e02b63465bf8da8428b60391d1af3d09ee2565374da697c43674a9aa344c391
|
| 3 |
+
size 4999831048
|
Qwen3-VL-8B-Caption-V4.5/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b8dc8838a44be212965024289e25d3cd2264d074489545e82d6c30c006c23de
|
| 3 |
+
size 2716270024
|
Qwen3-VL-8B-Caption-V4.5/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,757 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 17534247392
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 756 |
+
}
|
| 757 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/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 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/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 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a247885a17c87df8fb2eb7494b6186de26a4a2d2a2e29f755694d2e3e4cb32
|
| 3 |
+
size 11422922
|
Qwen3-VL-8B-Caption-V4.5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 60000,
|
| 235 |
+
"model_max_length": 262144,
|
| 236 |
+
"pad_to_multiple_of": null,
|
| 237 |
+
"pad_token": "<|endoftext|>",
|
| 238 |
+
"pad_token_type_id": 0,
|
| 239 |
+
"padding_side": "left",
|
| 240 |
+
"processor_class": "Qwen3VLProcessor",
|
| 241 |
+
"split_special_tokens": false,
|
| 242 |
+
"stride": 0,
|
| 243 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 244 |
+
"truncation_side": "right",
|
| 245 |
+
"truncation_strategy": "longest_first",
|
| 246 |
+
"unk_token": null,
|
| 247 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 248 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/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 |
+
}
|
Qwen3-VL-8B-Caption-V4.5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|