Commit ·
ea57de7
0
Parent(s):
Duplicate from Qwen/Qwen3-VL-Embedding-8B
Browse filesCo-authored-by: cheng <littlebird13@users.noreply.huggingface.co>
- .gitattributes +36 -0
- 1_Pooling/config.json +5 -0
- README.md +489 -0
- added_tokens.json +28 -0
- chat_template.jinja +125 -0
- config.json +65 -0
- config_sentence_transformers.json +11 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +757 -0
- modules.json +20 -0
- preprocessor_config.json +39 -0
- scripts/qwen3_vl_embedding.py +337 -0
- sentence_bert_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.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
|
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 4096,
|
| 3 |
+
"pooling_mode": "lasttoken",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,489 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
pipeline_tag: sentence-similarity
|
| 5 |
+
|
| 6 |
+
base_model:
|
| 7 |
+
- Qwen/Qwen3-VL-8B-Instruct
|
| 8 |
+
tags:
|
| 9 |
+
- sentence-transformers
|
| 10 |
+
- transformers
|
| 11 |
+
- multimodal embedding
|
| 12 |
+
- qwen
|
| 13 |
+
- embedding
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Qwen3-VL-Embedding-8B
|
| 17 |
+
|
| 18 |
+
<p align="center">
|
| 19 |
+
<img src="https://model-demo.oss-cn-hangzhou.aliyuncs.com/Qwen3-VL-Embedding.png" width="400"/>
|
| 20 |
+
<p>
|
| 21 |
+
|
| 22 |
+
## Highlights
|
| 23 |
+
|
| 24 |
+
The **Qwen3-VL-Embedding** and **Qwen3-VL-Reranker** model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities.
|
| 25 |
+
|
| 26 |
+
While the Embedding model generates high-dimensional vectors for broad applications like retrieval and clustering, the Reranker model is engineered to refine these results, establishing a comprehensive pipeline for state-of-the-art multimodal search.
|
| 27 |
+
|
| 28 |
+
- **Multimodal Versatility**: Both models seamlessly handle a wide range of inputs—including text, images, screenshots, and video—within a unified framework. They deliver state-of-the-art performance across diverse multimodal tasks such as image-text retrieval, video-text matching, visual question answering (VQA), and multimodal content clustering.
|
| 29 |
+
|
| 30 |
+
- **Unified Representation Learning (Embedding)**: By leveraging the Qwen3-VL architecture, the Embedding model generates semantically rich vectors that capture both visual and textual information in a shared space. This facilitates efficient similarity computation and retrieval across different modalities.
|
| 31 |
+
|
| 32 |
+
- **High-Precision Reranking (Reranker)**: We also introduce the Qwen3-VL-Reranker series to complement the embedding model. The reranker takes a (query, document) pair as input—where both query and document may contain arbitrary single or mixed modalities—and outputs a precise relevance score. In retrieval pipelines, the two models are typically used in tandem: the embedding model performs efficient initial recall, while the reranker refines results in a subsequent re-ranking stage. This two-stage approach significantly boosts retrieval accuracy.
|
| 33 |
+
|
| 34 |
+
- **Exceptional Practicality**: Inheriting Qwen3-VL’s multilingual capabilities, the series supports over 30 languages, making it ideal for global applications. It is highly practical for real-world scenarios, offering flexible vector dimensions, customizable instructions for specific use cases, and strong performance even with quantized embeddings. These capabilities enable developers to seamlessly integrate both models into existing pipelines, unlocking powerful cross-lingual and cross-modal understanding.
|
| 35 |
+
|
| 36 |
+
## Model Overview
|
| 37 |
+
|
| 38 |
+
**Qwen3-VL-Embedding-8B** has the following features:
|
| 39 |
+
|
| 40 |
+
- Model Type: MultiModal Embedding
|
| 41 |
+
- Supported Languages: 30+ Languages
|
| 42 |
+
- Supported Input Modalities: Text, images, screenshots, videos, and arbitrary multimodal combinations (e.g., text + image, text + video)
|
| 43 |
+
- Number of Parameters: 8B
|
| 44 |
+
- Context Length: 32k
|
| 45 |
+
- Embedding Dimension: Up to 4096, supports user-defined output dimensions ranging from 64 to 4096
|
| 46 |
+
|
| 47 |
+
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [technical report](https://arxiv.org/abs/2601.04720), [blog](https://qwen.ai/blog?id=qwen3-vl-embedding), [GitHub](https://github.com/QwenLM/Qwen3-VL-Embedding).
|
| 48 |
+
|
| 49 |
+
## Qwen3-VL-Embedding and Qwen3-VL-Reranker Model list
|
| 50 |
+
|
| 51 |
+
| Model | Size | Model Layers | Sequence Length | Embedding Dimension | Quantization Support | MRL Support | Instruction Aware |
|
| 52 |
+
|---|---|---|---|---|----------------------|---|---|
|
| 53 |
+
| [Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B) | 2B | 28 | 32K | 2048 | Yes | Yes | Yes |
|
| 54 |
+
| [Qwen3-VL-Embedding-8B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes | Yes |
|
| 55 |
+
| [Qwen3-VL-Reranker-2B](https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B) | 2B | 28 | 32K | - | - | - | Yes |
|
| 56 |
+
| [Qwen3-VL-Reranker-8B](https://huggingface.co/Qwen/Qwen3-VL-Reranker-8B) | 8B | 36 | 32K | - | - | - | Yes |
|
| 57 |
+
|
| 58 |
+
> **Note**:
|
| 59 |
+
> - `Quantization Support` indicates the supported quantization post process for the output embedding.
|
| 60 |
+
> - `MRL Support` indicates whether the embedding model supports custom dimensions for the final embedding.
|
| 61 |
+
> - `Instruction Aware` notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
|
| 62 |
+
> Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.
|
| 63 |
+
|
| 64 |
+
## Model Performance
|
| 65 |
+
|
| 66 |
+
### Evaluation Results on [MMEB-V2](https://huggingface.co/spaces/TIGER-Lab/MMEB-Leaderboard)
|
| 67 |
+
|
| 68 |
+
Results on the MMEB-V2 benchmark. All models except IFM-TTE have been re-evaluated on the updated VisDoc OOD split. CLS: classification, QA: question answering, RET: retrieval, GD: grounding, MRET: moment retrieval, VDR: ViDoRe, VR: VisRAG, OOD: out-of-distribution.
|
| 69 |
+
|
| 70 |
+
| Model | Model Size | Image CLS | Image QA | Image RET | Image GD | Image Overall | Video CLS | Video QA | Video RET | Video MRET | Video Overall | VisDoc VDRv1 | VisDoc VDRv2 | VisDoc VR | VisDoc OOD | VisDoc Overall | All |
|
| 71 |
+
|----------------------------|---------|-------|------|------|------|-----------|------|------|------|------|------|-------|------|--------|------|------|--------|
|
| 72 |
+
| **# of Datasets →** | | 10 | 10 | 12 | 4 | 36 | 5 | 5 | 5 | 3 | 18 | 10 | 4 | 6 | 4 | 24 | 78 |
|
| 73 |
+
| VLM2Vec | 2B | 58.7 | 49.3 | 65.0 | 72.9 | 59.7 | 33.4 | 30.5 | 20.6 | 30.7 | 28.6 | 49.8 | 13.5 | 51.8 | 48.2 | 44.0 | 47.7 |
|
| 74 |
+
| VLM2Vec-V2 | 2B | 62.9 | 56.3 | 69.5 | 77.3 | 64.9 | 39.3 | 34.3 | 28.8 | 36.8 | 34.6 | 75.5 | 44.9 | 79.4 | 62.2 | 69.2 | 59.2 |
|
| 75 |
+
| GME-2B | 2B | 54.4 | 29.9 | 66.9 | 55.5 | 51.9 | 34.9 | 42.0 | 25.6 | 31.1 | 33.6 | 86.1 | 54.0 | 82.5 | 67.5 | 76.8 | 55.3 |
|
| 76 |
+
| GME-7B | 7B | 57.7 | 34.7 | 71.2 | 59.3 | 56.0 | 37.4 | 50.4 | 28.4 | 37.0 | 38.4 | 89.4 | 55.6 | 85.0 | 68.3 | 79.3 | 59.1 |
|
| 77 |
+
| Ops-MM-embedding-v1 | 8B | 69.7 | 69.6 | 73.1 | 87.2 | 72.7 | 59.7 | 62.2 | 45.7 | 43.2 | 53.8 | 80.1 | 59.6 | 79.3 | 67.8 | 74.4 | 68.9 |
|
| 78 |
+
| IFM-TTE | 8B | 76.7 | 78.5 | 74.6 | 89.3 | 77.9 | 60.5 | 67.9 | 51.7 | 54.9 | 59.2 | 85.2 | 71.5 | 92.7 | 53.3 | 79.5 | 74.1 |
|
| 79 |
+
| RzenEmbed | 8B | 70.6 | 71.7 | 78.5 | 92.1 | 75.9 | 58.8 | 63.5 | 51.0 | 45.5 | 55.7 | 89.7 | 60.7 | 88.7 | 69.9 | 81.3 | 72.9 |
|
| 80 |
+
| Seed-1.6-embedding-1215 | unknown | 75.0 | 74.9 | 79.3 | 89.0 | 78.0 | 85.2 | 66.7 | 59.1 | 54.8 | 67.7 | 90.0 | 60.3 | 90.0 | 70.7 | 82.2 | 76.9 |
|
| 81 |
+
| **Qwen3-VL-Embedding-2B** | 2B | 70.2 | 74.4 | 74.9 | 88.6 | 75.0 | 72.8 | 63.8 | 52.3 | 51.6 | 61.1 | 85.2 | 66.0 | 86.3 | 74.3 | 80.2 | 73.4 |
|
| 82 |
+
| **Qwen3-VL-Embedding-8B** | 8B | 74.4 | 81.0 | 80.0 | 92.2 | 80.1 | 79.1 | 70.1 | 57.0 | 53.2 | 66.1 | 88.2 | 69.9 | 88.8 | 78.3 | 83.3 | **77.9** |
|
| 83 |
+
|
| 84 |
+
### Evaluation Results on [MMTEB](https://huggingface.co/spaces/mteb/leaderboard)
|
| 85 |
+
|
| 86 |
+
Results on the MMTEB benchmark.
|
| 87 |
+
|
| 88 |
+
| Model | Size | Mean (Task) | Mean (Type) | Bitxt Mining | Class. | Clust. | Inst. Retri. | Multi. Class. | Pair. Class. | Rerank | Retri. | STS |
|
| 89 |
+
|----------------------------------|:-------:|:-------------:|:-------------:|:--------------:|:--------:|:--------:|:--------------:|:---------------:|:--------------:|:--------:|:--------:|:------:|
|
| 90 |
+
| NV-Embed-v2 | 7B | 56.29 | 49.58 | 57.84 | 57.29 | 40.80 | 1.04 | 18.63 | 78.94 | 63.82 | 56.72 | 71.10|
|
| 91 |
+
| GritLM-7B | 7B | 60.92 | 53.74 | 70.53 | 61.83 | 49.75 | 3.45 | 22.77 | 79.94 | 63.78 | 58.31 | 73.33|
|
| 92 |
+
| BGE-M3 | 0.6B | 59.56 | 52.18 | 79.11 | 60.35 | 40.88 | -3.11 | 20.1 | 80.76 | 62.79 | 54.60 | 74.12|
|
| 93 |
+
| multilingual-e5-large-instruct | 0.6B | 63.22 | 55.08 | 80.13 | 64.94 | 50.75 | -0.40 | 22.91 | 80.86 | 62.61 | 57.12 | 76.81|
|
| 94 |
+
| gte-Qwen2-1.5B-instruct | 1.5B | 59.45 | 52.69 | 62.51 | 58.32 | 52.05 | 0.74 | 24.02 | 81.58 | 62.58 | 60.78 | 71.61|
|
| 95 |
+
| gte-Qwen2-7b-Instruct | 7B | 62.51 | 55.93 | 73.92 | 61.55 | 52.77 | 4.94 | 25.48 | 85.13 | 65.55 | 60.08 | 73.98|
|
| 96 |
+
| text-embedding-3-large | - | 58.93 | 51.41 | 62.17 | 60.27 | 46.89 | -2.68 | 22.03 | 79.17 | 63.89 | 59.27 | 71.68|
|
| 97 |
+
| Cohere-embed-multilingual-v3.0 | - | 61.12 | 53.23 | 70.50 | 62.95 | 46.89 | -1.89 | 22.74 | 79.88 | 64.07 | 59.16 | 74.80|
|
| 98 |
+
| Gemini Embedding | - | 68.37 | 59.59 | 79.28 | 71.82 | 54.59 | 5.18 | **29.16** | 83.63 | 65.58 | 67.71 | 79.40|
|
| 99 |
+
| Qwen3-Embedding-0.6B | 0.6B | 64.33 | 56.00 | 72.22 | 66.83 | 52.33 | 5.09 | 24.59 | 80.83 | 61.41 | 64.64 | 76.17|
|
| 100 |
+
| Qwen3-Embedding-4B | 4B | 69.45 | 60.86 | 79.36 | 72.33 | 57.15 | **11.56** | 26.77 | 85.05 | 65.08 | 69.60 | 80.86|
|
| 101 |
+
| Qwen3-Embedding-8B | 8B | **70.58** | **61.69** | **80.89** | **74.00** | **57.65** | 10.06 | 28.66 | **86.40** | **65.63** | **70.88** | **81.08** |
|
| 102 |
+
| Qwen3-VL-Embedding-2B | 2B | 63.87 | 55.84 | 69.51 | 65.86 | 52.50 | 3.87 | 26.08 | 78.50 | 64.80 | 67.12 | 74.29 |
|
| 103 |
+
| Qwen3-VL-Embedding-8B | 8B | 67.88 | 58.88 | 77.48 | 71.95 | 55.82 | 4.46 | 28.59 | 81.08 | 65.72 | 69.41 | 75.41 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
## Usage
|
| 107 |
+
|
| 108 |
+
### Sentence Transformers
|
| 109 |
+
|
| 110 |
+
Install Sentence Transformers with `pip install sentence-transformers`, then use the model like this:
|
| 111 |
+
|
| 112 |
+
```python
|
| 113 |
+
from sentence_transformers import SentenceTransformer
|
| 114 |
+
|
| 115 |
+
# Load the model
|
| 116 |
+
model = SentenceTransformer("Qwen/Qwen3-VL-Embedding-8B")
|
| 117 |
+
|
| 118 |
+
# Text queries
|
| 119 |
+
queries = [
|
| 120 |
+
"A woman playing with her dog on a beach at sunset.",
|
| 121 |
+
"Pet owner training dog outdoors near water.",
|
| 122 |
+
"Woman surfing on waves during a sunny day.",
|
| 123 |
+
"City skyline view from a high-rise building at night.",
|
| 124 |
+
]
|
| 125 |
+
|
| 126 |
+
# Documents: text, image, and text+image
|
| 127 |
+
documents = [
|
| 128 |
+
"A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.",
|
| 129 |
+
"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 130 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
|
| 131 |
+
]
|
| 132 |
+
|
| 133 |
+
# Encode queries and documents
|
| 134 |
+
query_embeddings = model.encode(queries)
|
| 135 |
+
doc_embeddings = model.encode(documents)
|
| 136 |
+
print(query_embeddings.shape, doc_embeddings.shape)
|
| 137 |
+
# (4, 4096) (3, 4096)
|
| 138 |
+
|
| 139 |
+
# Compute similarities
|
| 140 |
+
similarities = model.similarity(query_embeddings, doc_embeddings)
|
| 141 |
+
print(similarities)
|
| 142 |
+
# tensor([[0.7438, 0.6556, 0.6244],
|
| 143 |
+
# [0.4430, 0.3323, 0.3929],
|
| 144 |
+
# [0.3685, 0.2310, 0.2874],
|
| 145 |
+
# [0.0602, -0.0162, 0.0167]])
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
By default, all inputs are wrapped with the `"Represent the user's input."` instruction via a system prompt. You can customize this by passing a different prompt:
|
| 149 |
+
|
| 150 |
+
```python
|
| 151 |
+
# With a custom prompt
|
| 152 |
+
model.encode(queries, prompt="Retrieve relevant documents for the query.")
|
| 153 |
+
```
|
| 154 |
+
|
| 155 |
+
### Using transformers
|
| 156 |
+
|
| 157 |
+
- **requirements**
|
| 158 |
+
```text
|
| 159 |
+
transformers>=4.57.0
|
| 160 |
+
qwen-vl-utils>=0.0.14
|
| 161 |
+
torch==2.8.0
|
| 162 |
+
```
|
| 163 |
+
|
| 164 |
+
### Basic Usage Example
|
| 165 |
+
|
| 166 |
+
```python
|
| 167 |
+
from scripts.qwen3_vl_embedding import Qwen3VLEmbedder
|
| 168 |
+
|
| 169 |
+
# Define a list of query texts
|
| 170 |
+
queries = [
|
| 171 |
+
{"text": "A woman playing with her dog on a beach at sunset."},
|
| 172 |
+
{"text": "Pet owner training dog outdoors near water."},
|
| 173 |
+
{"text": "Woman surfing on waves during a sunny day."},
|
| 174 |
+
{"text": "City skyline view from a high-rise building at night."}
|
| 175 |
+
]
|
| 176 |
+
|
| 177 |
+
# Define a list of document texts and images
|
| 178 |
+
documents = [
|
| 179 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."},
|
| 180 |
+
{"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
|
| 181 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}
|
| 182 |
+
]
|
| 183 |
+
|
| 184 |
+
# Specify the model path
|
| 185 |
+
model_name_or_path = "Qwen/Qwen3-VL-Embedding-8B"
|
| 186 |
+
|
| 187 |
+
# Initialize the Qwen3VLEmbedder model
|
| 188 |
+
model = Qwen3VLEmbedder(model_name_or_path=model_name_or_path)
|
| 189 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving,
|
| 190 |
+
# model = Qwen3VLEmbedder(model_name_or_path=model_name_or_path, torch_dtype=torch.float16, attn_implementation="flash_attention_2")
|
| 191 |
+
|
| 192 |
+
# Combine queries and documents into a single input list
|
| 193 |
+
inputs = queries + documents
|
| 194 |
+
|
| 195 |
+
# Process the inputs to get embeddings
|
| 196 |
+
embeddings = model.process(inputs)
|
| 197 |
+
|
| 198 |
+
# Compute similarity scores between query embeddings and document embeddings
|
| 199 |
+
similarity_scores = (embeddings[:4] @ embeddings[4:].T)
|
| 200 |
+
|
| 201 |
+
# Print out the similarity scores in a list format
|
| 202 |
+
print(similarity_scores.tolist())
|
| 203 |
+
|
| 204 |
+
# [[0.74267578125, 0.6630859375, 0.6328125], [0.443603515625, 0.33349609375, 0.396484375], [0.3671875, 0.2354736328125, 0.289306640625], [0.060821533203125, -0.01557159423828125, 0.0165863037109375]]
|
| 205 |
+
```
|
| 206 |
+
|
| 207 |
+
### vLLM Basic Usage Example
|
| 208 |
+
```python
|
| 209 |
+
import argparse
|
| 210 |
+
import numpy as np
|
| 211 |
+
import os
|
| 212 |
+
from typing import List, Dict, Any
|
| 213 |
+
from vllm import LLM, EngineArgs
|
| 214 |
+
from vllm.multimodal.utils import fetch_image
|
| 215 |
+
|
| 216 |
+
|
| 217 |
+
# Define a list of query texts
|
| 218 |
+
queries = [
|
| 219 |
+
{"text": "A woman playing with her dog on a beach at sunset."},
|
| 220 |
+
{"text": "Pet owner training dog outdoors near water."},
|
| 221 |
+
{"text": "Woman surfing on waves during a sunny day."},
|
| 222 |
+
{"text": "City skyline view from a high-rise building at night."}
|
| 223 |
+
]
|
| 224 |
+
|
| 225 |
+
# Define a list of document texts and images
|
| 226 |
+
documents = [
|
| 227 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."},
|
| 228 |
+
{"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
|
| 229 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}
|
| 230 |
+
]
|
| 231 |
+
|
| 232 |
+
def format_input_to_conversation(input_dict: Dict[str, Any], instruction: str = "Represent the user's input.") -> List[Dict]:
|
| 233 |
+
content = []
|
| 234 |
+
|
| 235 |
+
text = input_dict.get('text')
|
| 236 |
+
image = input_dict.get('image')
|
| 237 |
+
|
| 238 |
+
if image:
|
| 239 |
+
image_content = None
|
| 240 |
+
if isinstance(image, str):
|
| 241 |
+
if image.startswith(('http', 'https', 'oss')):
|
| 242 |
+
image_content = image
|
| 243 |
+
else:
|
| 244 |
+
abs_image_path = os.path.abspath(image)
|
| 245 |
+
image_content = 'file://' + abs_image_path
|
| 246 |
+
else:
|
| 247 |
+
image_content = image
|
| 248 |
+
|
| 249 |
+
if image_content:
|
| 250 |
+
content.append({
|
| 251 |
+
'type': 'image',
|
| 252 |
+
'image': image_content,
|
| 253 |
+
})
|
| 254 |
+
|
| 255 |
+
if text:
|
| 256 |
+
content.append({'type': 'text', 'text': text})
|
| 257 |
+
|
| 258 |
+
if not content:
|
| 259 |
+
content.append({'type': 'text', 'text': ""})
|
| 260 |
+
|
| 261 |
+
conversation = [
|
| 262 |
+
{"role": "system", "content": [{"type": "text", "text": instruction}]},
|
| 263 |
+
{"role": "user", "content": content}
|
| 264 |
+
]
|
| 265 |
+
|
| 266 |
+
return conversation
|
| 267 |
+
|
| 268 |
+
def prepare_vllm_inputs(input_dict: Dict[str, Any], llm, instruction: str = "Represent the user's input.") -> Dict[str, Any]:
|
| 269 |
+
text = input_dict.get('text')
|
| 270 |
+
image = input_dict.get('image')
|
| 271 |
+
|
| 272 |
+
conversation = format_input_to_conversation(input_dict, instruction)
|
| 273 |
+
|
| 274 |
+
prompt_text = llm.llm_engine.tokenizer.apply_chat_template(
|
| 275 |
+
conversation,
|
| 276 |
+
tokenize=False,
|
| 277 |
+
add_generation_prompt=True
|
| 278 |
+
)
|
| 279 |
+
|
| 280 |
+
multi_modal_data = None
|
| 281 |
+
if image:
|
| 282 |
+
if isinstance(image, str):
|
| 283 |
+
if image.startswith(('http', 'https', 'oss')):
|
| 284 |
+
try:
|
| 285 |
+
image_obj = fetch_image(image)
|
| 286 |
+
multi_modal_data = {"image": image_obj}
|
| 287 |
+
except Exception as e:
|
| 288 |
+
print(f"Warning: Failed to fetch image {image}: {e}")
|
| 289 |
+
else:
|
| 290 |
+
abs_image_path = os.path.abspath(image)
|
| 291 |
+
if os.path.exists(abs_image_path):
|
| 292 |
+
from PIL import Image
|
| 293 |
+
image_obj = Image.open(abs_image_path)
|
| 294 |
+
multi_modal_data = {"image": image_obj}
|
| 295 |
+
else:
|
| 296 |
+
print(f"Warning: Image file not found: {abs_image_path}")
|
| 297 |
+
else:
|
| 298 |
+
multi_modal_data = {"image": image}
|
| 299 |
+
|
| 300 |
+
result = {
|
| 301 |
+
"prompt": prompt_text,
|
| 302 |
+
"multi_modal_data": multi_modal_data
|
| 303 |
+
}
|
| 304 |
+
return result
|
| 305 |
+
|
| 306 |
+
def main():
|
| 307 |
+
parser = argparse.ArgumentParser(description="Offline Similarity Check with vLLM")
|
| 308 |
+
parser.add_argument("--model-path", type=str, default="models/Qwen3-VL-Embedding-8B", help="Path to the model")
|
| 309 |
+
parser.add_argument("--dtype", type=str, default="bfloat16", help="Data type (e.g., bfloat16)")
|
| 310 |
+
args = parser.parse_args()
|
| 311 |
+
|
| 312 |
+
print(f"Loading model from {args.model_path}...")
|
| 313 |
+
|
| 314 |
+
engine_args = EngineArgs(
|
| 315 |
+
model=args.model_path,
|
| 316 |
+
runner="pooling",
|
| 317 |
+
dtype=args.dtype,
|
| 318 |
+
trust_remote_code=True,
|
| 319 |
+
)
|
| 320 |
+
|
| 321 |
+
llm = LLM(**vars(engine_args))
|
| 322 |
+
|
| 323 |
+
all_inputs = queries + documents
|
| 324 |
+
vllm_inputs = [prepare_vllm_inputs(inp, llm) for inp in all_inputs]
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
outputs = llm.embed(vllm_inputs)
|
| 328 |
+
|
| 329 |
+
embeddings_list = []
|
| 330 |
+
for i, output in enumerate(outputs):
|
| 331 |
+
emb = output.outputs.embedding
|
| 332 |
+
embeddings_list.append(emb)
|
| 333 |
+
print(f"Input {i} embedding shape: {len(emb)}")
|
| 334 |
+
|
| 335 |
+
embeddings = np.array(embeddings_list)
|
| 336 |
+
print(f"\nEmbeddings shape: {embeddings.shape}")
|
| 337 |
+
|
| 338 |
+
num_queries = len(queries)
|
| 339 |
+
query_embeddings = embeddings[:num_queries]
|
| 340 |
+
doc_embeddings = embeddings[num_queries:]
|
| 341 |
+
|
| 342 |
+
similarity_scores = query_embeddings @ doc_embeddings.T
|
| 343 |
+
|
| 344 |
+
print("\nSimilarity Scores:")
|
| 345 |
+
print(similarity_scores.tolist())
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
if __name__ == "__main__":
|
| 349 |
+
main()
|
| 350 |
+
```
|
| 351 |
+
|
| 352 |
+
### SGLang Basic Usage Example
|
| 353 |
+
```python
|
| 354 |
+
import argparse
|
| 355 |
+
import numpy as np
|
| 356 |
+
import torch
|
| 357 |
+
import os
|
| 358 |
+
from typing import List, Dict, Any
|
| 359 |
+
from sglang.srt.entrypoints.engine import Engine
|
| 360 |
+
|
| 361 |
+
# Define a list of query texts
|
| 362 |
+
queries = [
|
| 363 |
+
{"text": "A woman playing with her dog on a beach at sunset."},
|
| 364 |
+
{"text": "Pet owner training dog outdoors near water."},
|
| 365 |
+
{"text": "Woman surfing on waves during a sunny day."},
|
| 366 |
+
{"text": "City skyline view from a high-rise building at night."}
|
| 367 |
+
]
|
| 368 |
+
|
| 369 |
+
# Define a list of document texts and images
|
| 370 |
+
documents = [
|
| 371 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."},
|
| 372 |
+
{"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
|
| 373 |
+
{"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}
|
| 374 |
+
]
|
| 375 |
+
|
| 376 |
+
def format_input_to_conversation(input_dict: Dict[str, Any], instruction: str = "Represent the user's input.") -> List[Dict]:
|
| 377 |
+
content = []
|
| 378 |
+
|
| 379 |
+
text = input_dict.get('text')
|
| 380 |
+
image = input_dict.get('image')
|
| 381 |
+
|
| 382 |
+
if image:
|
| 383 |
+
image_content = None
|
| 384 |
+
if isinstance(image, str):
|
| 385 |
+
if image.startswith(('http', 'oss')):
|
| 386 |
+
image_content = image
|
| 387 |
+
else:
|
| 388 |
+
abs_image_path = os.path.abspath(image)
|
| 389 |
+
image_content = 'file://' + abs_image_path
|
| 390 |
+
else:
|
| 391 |
+
image_content = image
|
| 392 |
+
if image_content:
|
| 393 |
+
content.append({
|
| 394 |
+
'type': 'image', 'image': image_content,
|
| 395 |
+
})
|
| 396 |
+
|
| 397 |
+
if text:
|
| 398 |
+
content.append({'type': 'text', 'text': text})
|
| 399 |
+
|
| 400 |
+
if not content:
|
| 401 |
+
content.append({'type': 'text', 'text': ""})
|
| 402 |
+
|
| 403 |
+
conversation = [
|
| 404 |
+
{"role": "system", "content": [{"type": "text", "text": instruction}]},
|
| 405 |
+
{"role": "user", "content": content}
|
| 406 |
+
]
|
| 407 |
+
|
| 408 |
+
return conversation
|
| 409 |
+
|
| 410 |
+
def convert_to_sglang_format(input_dict: Dict[str, Any], engine: Engine, instruction: str = "Represent the user's input.") -> Dict[str, Any]:
|
| 411 |
+
conversation = format_input_to_conversation(input_dict, instruction)
|
| 412 |
+
|
| 413 |
+
text_for_api = engine.tokenizer_manager.tokenizer.apply_chat_template(
|
| 414 |
+
conversation,
|
| 415 |
+
tokenize=False,
|
| 416 |
+
add_generation_prompt=True
|
| 417 |
+
)
|
| 418 |
+
|
| 419 |
+
result = {"text": text_for_api}
|
| 420 |
+
|
| 421 |
+
image = input_dict.get('image')
|
| 422 |
+
if image and isinstance(image, str):
|
| 423 |
+
result["image"] = image
|
| 424 |
+
|
| 425 |
+
|
| 426 |
+
return result
|
| 427 |
+
|
| 428 |
+
def main():
|
| 429 |
+
parser = argparse.ArgumentParser(description="Offline Similarity Check with SGLang")
|
| 430 |
+
parser.add_argument("--model-path", type=str, default="models/Qwen3-VL-Embedding-8B", help="Path to the model")
|
| 431 |
+
parser.add_argument("--dtype", type=str, default="bfloat16", help="Data type (e.g., bfloat16)")
|
| 432 |
+
args = parser.parse_args()
|
| 433 |
+
|
| 434 |
+
print(f"Loading model from {args.model_path}...")
|
| 435 |
+
|
| 436 |
+
engine = Engine(
|
| 437 |
+
model_path=args.model_path,
|
| 438 |
+
is_embedding=True,
|
| 439 |
+
dtype=args.dtype,
|
| 440 |
+
trust_remote_code=True,
|
| 441 |
+
)
|
| 442 |
+
|
| 443 |
+
inputs = queries + documents
|
| 444 |
+
sglang_inputs = [convert_to_sglang_format(inp, engine) for inp in inputs]
|
| 445 |
+
print(sglang_inputs[:])
|
| 446 |
+
print(f"sglang_inputs: {sglang_inputs}")
|
| 447 |
+
print(f"Processing {len(sglang_inputs)} inputs...")
|
| 448 |
+
|
| 449 |
+
prompts = [inp['text'] for inp in sglang_inputs]
|
| 450 |
+
images = [inp.get('image') for inp in sglang_inputs]
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
results = engine.encode(prompts, image_data=images)
|
| 454 |
+
|
| 455 |
+
embeddings_list = []
|
| 456 |
+
for res in results:
|
| 457 |
+
embeddings_list.append(res['embedding'])
|
| 458 |
+
|
| 459 |
+
embeddings = np.array(embeddings_list)
|
| 460 |
+
print(f"Embeddings shape: {embeddings.shape}")
|
| 461 |
+
|
| 462 |
+
num_queries = len(queries)
|
| 463 |
+
query_embeddings = embeddings[:num_queries]
|
| 464 |
+
doc_embeddings = embeddings[num_queries:]
|
| 465 |
+
|
| 466 |
+
similarity_scores = (query_embeddings @ doc_embeddings.T)
|
| 467 |
+
|
| 468 |
+
print("\nSimilarity Scores:")
|
| 469 |
+
print(similarity_scores.tolist())
|
| 470 |
+
|
| 471 |
+
if __name__ == "__main__":
|
| 472 |
+
main()
|
| 473 |
+
```
|
| 474 |
+
|
| 475 |
+
For more usage examples, please visit our [GitHub repository](https://github.com/QwenLM/Qwen3-VL-Embedding).
|
| 476 |
+
|
| 477 |
+
|
| 478 |
+
## Citation
|
| 479 |
+
|
| 480 |
+
If you find our work helpful, feel free to give us a cite.
|
| 481 |
+
|
| 482 |
+
```
|
| 483 |
+
@article{qwen3vlembedding,
|
| 484 |
+
title={Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking},
|
| 485 |
+
author={Li, Mingxin and Zhang, Yanzhao and Long, Dingkun and Chen Keqin and Song, Sibo and Bai, Shuai and Yang, Zhibo and Xie, Pengjun and Yang, An and Liu, Dayiheng and Zhou, Jingren and Lin, Junyang},
|
| 486 |
+
journal={arXiv preprint arXiv:2601.04720},
|
| 487 |
+
year={2026}
|
| 488 |
+
}
|
| 489 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set default_system_message = 'Represent the user\'s input.' -%}
|
| 2 |
+
{%- if tools %}
|
| 3 |
+
{{- '<|im_start|>system\n' }}
|
| 4 |
+
{%- if messages[0].role == 'system' %}
|
| 5 |
+
{%- if messages[0].content is string %}
|
| 6 |
+
{{- messages[0].content }}
|
| 7 |
+
{%- else %}
|
| 8 |
+
{%- for content in messages[0].content %}
|
| 9 |
+
{%- if 'text' in content %}
|
| 10 |
+
{{- content.text }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{{- '\n\n' }}
|
| 15 |
+
{%- else %}
|
| 16 |
+
{{- default_system_message + '\n\n' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- "# 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>" }}
|
| 19 |
+
{%- for tool in tools %}
|
| 20 |
+
{{- "\n" }}
|
| 21 |
+
{{- tool | tojson }}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
{{- "\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" }}
|
| 24 |
+
{%- else %}
|
| 25 |
+
{%- if messages[0].role == 'system' %}
|
| 26 |
+
{{- '<|im_start|>system\n' }}
|
| 27 |
+
{%- if messages[0].content is string %}
|
| 28 |
+
{{- messages[0].content }}
|
| 29 |
+
{%- else %}
|
| 30 |
+
{%- for content in messages[0].content %}
|
| 31 |
+
{%- if 'text' in content %}
|
| 32 |
+
{{- content.text }}
|
| 33 |
+
{%- endif %}
|
| 34 |
+
{%- endfor %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{{- '<|im_end|>\n' }}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{{- '<|im_start|>system\n' + default_system_message + '<|im_end|>\n' }}
|
| 39 |
+
{%- endif %}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- set image_count = namespace(value=0) %}
|
| 42 |
+
{%- set video_count = namespace(value=0) %}
|
| 43 |
+
{%- for message in messages %}
|
| 44 |
+
{%- if message.role == "user" %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 46 |
+
{%- if message.content is string %}
|
| 47 |
+
{{- message.content }}
|
| 48 |
+
{%- else %}
|
| 49 |
+
{%- for content in message.content %}
|
| 50 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 51 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 52 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 53 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 54 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 55 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 56 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 57 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 58 |
+
{%- elif 'text' in content %}
|
| 59 |
+
{{- content.text }}
|
| 60 |
+
{%- endif %}
|
| 61 |
+
{%- endfor %}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{{- '<|im_end|>\n' }}
|
| 64 |
+
{%- elif message.role == "assistant" %}
|
| 65 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 66 |
+
{%- if message.content is string %}
|
| 67 |
+
{{- message.content }}
|
| 68 |
+
{%- else %}
|
| 69 |
+
{%- for content_item in message.content %}
|
| 70 |
+
{%- if 'text' in content_item %}
|
| 71 |
+
{{- content_item.text }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- endfor %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if message.tool_calls %}
|
| 76 |
+
{%- for tool_call in message.tool_calls %}
|
| 77 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 78 |
+
{{- '\n' }}
|
| 79 |
+
{%- endif %}
|
| 80 |
+
{%- if tool_call.function %}
|
| 81 |
+
{%- set tool_call = tool_call.function %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 84 |
+
{{- tool_call.name }}
|
| 85 |
+
{{- '", "arguments": ' }}
|
| 86 |
+
{%- if tool_call.arguments is string %}
|
| 87 |
+
{{- tool_call.arguments }}
|
| 88 |
+
{%- else %}
|
| 89 |
+
{{- tool_call.arguments | tojson }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{{- '}\n</tool_call>' }}
|
| 92 |
+
{%- endfor %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '<|im_end|>\n' }}
|
| 95 |
+
{%- elif message.role == "tool" %}
|
| 96 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 97 |
+
{{- '<|im_start|>user' }}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{{- '\n<tool_response>\n' }}
|
| 100 |
+
{%- if message.content is string %}
|
| 101 |
+
{{- message.content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{%- for content in message.content %}
|
| 104 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 105 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 106 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 107 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 108 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 109 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 110 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 111 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 112 |
+
{%- elif 'text' in content %}
|
| 113 |
+
{{- content.text }}
|
| 114 |
+
{%- endif %}
|
| 115 |
+
{%- endfor %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{{- '\n</tool_response>' }}
|
| 118 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 119 |
+
{{- '<|im_end|>\n' }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{%- endif %}
|
| 122 |
+
{%- endfor %}
|
| 123 |
+
{%- if add_generation_prompt %}
|
| 124 |
+
{{- '<|im_start|>assistant\n' }}
|
| 125 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"text_config": {
|
| 9 |
+
"attention_bias": false,
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 151643,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 151645,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 12288,
|
| 19 |
+
"max_position_embeddings": 262144,
|
| 20 |
+
"model_type": "qwen3_vl_text",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 36,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_scaling": {
|
| 26 |
+
"mrope_interleaved": true,
|
| 27 |
+
"mrope_section": [
|
| 28 |
+
24,
|
| 29 |
+
20,
|
| 30 |
+
20
|
| 31 |
+
],
|
| 32 |
+
"rope_type": "default"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 5000000,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 151936
|
| 37 |
+
},
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"transformers_version": "4.57.1",
|
| 40 |
+
"use_cache": false,
|
| 41 |
+
"video_token_id": 151656,
|
| 42 |
+
"vision_config": {
|
| 43 |
+
"deepstack_visual_indexes": [
|
| 44 |
+
8,
|
| 45 |
+
16,
|
| 46 |
+
24
|
| 47 |
+
],
|
| 48 |
+
"depth": 27,
|
| 49 |
+
"dtype": "bfloat16",
|
| 50 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 51 |
+
"hidden_size": 1152,
|
| 52 |
+
"in_channels": 3,
|
| 53 |
+
"initializer_range": 0.02,
|
| 54 |
+
"intermediate_size": 4304,
|
| 55 |
+
"model_type": "qwen3_vl",
|
| 56 |
+
"num_heads": 16,
|
| 57 |
+
"num_position_embeddings": 2304,
|
| 58 |
+
"out_hidden_size": 4096,
|
| 59 |
+
"patch_size": 16,
|
| 60 |
+
"spatial_merge_size": 2,
|
| 61 |
+
"temporal_patch_size": 2
|
| 62 |
+
},
|
| 63 |
+
"vision_end_token_id": 151653,
|
| 64 |
+
"vision_start_token_id": 151652
|
| 65 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.4.0"
|
| 4 |
+
},
|
| 5 |
+
"default_prompt_name": "default",
|
| 6 |
+
"model_type": "SentenceTransformer",
|
| 7 |
+
"prompts": {
|
| 8 |
+
"default": "Represent the user's input."
|
| 9 |
+
},
|
| 10 |
+
"similarity_fn_name": "cosine"
|
| 11 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79ef275ec5f751d5fb59357c00d473268f9fd74abf5e38aa30137d268e7733c4
|
| 3 |
+
size 4998056552
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4da61f512e84fc0f0b80bcb7bcc5137eb3bf25b658a7d55f84f4056078545f0
|
| 3 |
+
size 4915962464
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fb17cf8f06d6fe5aaacf114e85c4e6d8318799f24b517f50d1ec154a8d47007
|
| 3 |
+
size 4915962496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:000213b6d1d03ed9023fac23716da51ec4c5be221a04526c2f732d31d8fed1f5
|
| 3 |
+
size 1459698112
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,757 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8144793840,
|
| 4 |
+
"total_size": 16289587680
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 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-00003-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-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-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-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-00004-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-00004-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-00002-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-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-00002-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-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 756 |
+
}
|
| 757 |
+
}
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
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": 1310720,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": 4096,
|
| 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": 1310720,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
scripts/qwen3_vl_embedding.py
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn.functional as F
|
| 3 |
+
import unicodedata
|
| 4 |
+
import numpy as np
|
| 5 |
+
import logging
|
| 6 |
+
|
| 7 |
+
from PIL import Image
|
| 8 |
+
from dataclasses import dataclass
|
| 9 |
+
from typing import Optional, List, Union, Dict, Any
|
| 10 |
+
from transformers.models.qwen3_vl.modeling_qwen3_vl import Qwen3VLPreTrainedModel, Qwen3VLModel, Qwen3VLConfig
|
| 11 |
+
from transformers.models.qwen3_vl.processing_qwen3_vl import Qwen3VLProcessor
|
| 12 |
+
from transformers.modeling_outputs import ModelOutput
|
| 13 |
+
from transformers.processing_utils import Unpack
|
| 14 |
+
from transformers.utils import TransformersKwargs
|
| 15 |
+
from transformers.cache_utils import Cache
|
| 16 |
+
from transformers.utils.generic import check_model_inputs
|
| 17 |
+
from qwen_vl_utils.vision_process import process_vision_info
|
| 18 |
+
|
| 19 |
+
logger = logging.getLogger(__name__)
|
| 20 |
+
|
| 21 |
+
# Constants for configuration
|
| 22 |
+
MAX_LENGTH = 8192
|
| 23 |
+
IMAGE_BASE_FACTOR = 16
|
| 24 |
+
IMAGE_FACTOR = IMAGE_BASE_FACTOR * 2
|
| 25 |
+
MIN_PIXELS = 4 * IMAGE_FACTOR * IMAGE_FACTOR
|
| 26 |
+
MAX_PIXELS = 1800 * IMAGE_FACTOR * IMAGE_FACTOR
|
| 27 |
+
FPS = 1
|
| 28 |
+
MAX_FRAMES = 64
|
| 29 |
+
FRAME_MAX_PIXELS = 768 * IMAGE_FACTOR * IMAGE_FACTOR
|
| 30 |
+
MAX_TOTAL_PIXELS = 10 * FRAME_MAX_PIXELS
|
| 31 |
+
PAD_TOKEN = "<|endoftext|>"
|
| 32 |
+
|
| 33 |
+
# Define output structure for embeddings
|
| 34 |
+
@dataclass
|
| 35 |
+
class Qwen3VLForEmbeddingOutput(ModelOutput):
|
| 36 |
+
last_hidden_state: Optional[torch.FloatTensor] = None
|
| 37 |
+
attention_mask: Optional[torch.Tensor] = None
|
| 38 |
+
|
| 39 |
+
# Define model class to compute embeddings
|
| 40 |
+
class Qwen3VLForEmbedding(Qwen3VLPreTrainedModel):
|
| 41 |
+
_checkpoint_conversion_mapping = {}
|
| 42 |
+
accepts_loss_kwargs = False
|
| 43 |
+
config: Qwen3VLConfig
|
| 44 |
+
|
| 45 |
+
def __init__(self, config):
|
| 46 |
+
super().__init__(config)
|
| 47 |
+
self.model = Qwen3VLModel(config)
|
| 48 |
+
self.post_init()
|
| 49 |
+
|
| 50 |
+
def get_input_embeddings(self):
|
| 51 |
+
return self.model.get_input_embeddings()
|
| 52 |
+
|
| 53 |
+
def set_input_embeddings(self, value):
|
| 54 |
+
self.model.set_input_embeddings(value)
|
| 55 |
+
|
| 56 |
+
def set_decoder(self, decoder):
|
| 57 |
+
self.model.set_decoder(decoder)
|
| 58 |
+
|
| 59 |
+
def get_decoder(self):
|
| 60 |
+
return self.model.get_decoder()
|
| 61 |
+
|
| 62 |
+
# Extract video features from model
|
| 63 |
+
def get_video_features(self, pixel_values_videos: torch.FloatTensor,
|
| 64 |
+
video_grid_thw: Optional[torch.LongTensor] = None):
|
| 65 |
+
return self.model.get_video_features(pixel_values_videos, video_grid_thw)
|
| 66 |
+
|
| 67 |
+
# Extract image features from model
|
| 68 |
+
def get_image_features(self, pixel_values: torch.FloatTensor,
|
| 69 |
+
image_grid_thw: Optional[torch.LongTensor] = None):
|
| 70 |
+
return self.model.get_image_features(pixel_values, image_grid_thw)
|
| 71 |
+
|
| 72 |
+
# Make modules accessible through properties
|
| 73 |
+
@property
|
| 74 |
+
def language_model(self):
|
| 75 |
+
return self.model.language_model
|
| 76 |
+
|
| 77 |
+
@property
|
| 78 |
+
def visual(self):
|
| 79 |
+
return self.model.visual
|
| 80 |
+
|
| 81 |
+
# Forward pass through model with input parameters
|
| 82 |
+
# @check_model_inputs
|
| 83 |
+
def forward(self,
|
| 84 |
+
input_ids: torch.LongTensor = None,
|
| 85 |
+
attention_mask: Optional[torch.Tensor] = None,
|
| 86 |
+
position_ids: Optional[torch.LongTensor] = None,
|
| 87 |
+
past_key_values: Optional[Cache] = None,
|
| 88 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
| 89 |
+
pixel_values: Optional[torch.Tensor] = None,
|
| 90 |
+
pixel_values_videos: Optional[torch.FloatTensor] = None,
|
| 91 |
+
image_grid_thw: Optional[torch.LongTensor] = None,
|
| 92 |
+
video_grid_thw: Optional[torch.LongTensor] = None,
|
| 93 |
+
cache_position: Optional[torch.LongTensor] = None,
|
| 94 |
+
logits_to_keep: Union[int, torch.Tensor] = 0,
|
| 95 |
+
**kwargs: Unpack[TransformersKwargs],
|
| 96 |
+
) -> Union[tuple, Qwen3VLForEmbeddingOutput]:
|
| 97 |
+
# Pass inputs through the model
|
| 98 |
+
outputs = self.model(
|
| 99 |
+
input_ids=input_ids,
|
| 100 |
+
pixel_values=pixel_values,
|
| 101 |
+
pixel_values_videos=pixel_values_videos,
|
| 102 |
+
image_grid_thw=image_grid_thw,
|
| 103 |
+
video_grid_thw=video_grid_thw,
|
| 104 |
+
position_ids=position_ids,
|
| 105 |
+
attention_mask=attention_mask,
|
| 106 |
+
past_key_values=past_key_values,
|
| 107 |
+
inputs_embeds=inputs_embeds,
|
| 108 |
+
cache_position=cache_position,
|
| 109 |
+
**kwargs,
|
| 110 |
+
)
|
| 111 |
+
# Return the model output
|
| 112 |
+
return Qwen3VLForEmbeddingOutput(
|
| 113 |
+
last_hidden_state=outputs.last_hidden_state,
|
| 114 |
+
attention_mask=attention_mask,
|
| 115 |
+
)
|
| 116 |
+
|
| 117 |
+
def sample_frames(frames: List[Union[str, Image.Image]], num_segments: int, max_segments: int) -> List[str]:
|
| 118 |
+
duration = len(frames)
|
| 119 |
+
frame_id_array = np.linspace(0, duration - 1, num_segments, dtype=int)
|
| 120 |
+
frame_id_list = frame_id_array.tolist()
|
| 121 |
+
last_frame_id = frame_id_list[-1]
|
| 122 |
+
|
| 123 |
+
# Create a list of sampled frames
|
| 124 |
+
sampled_frames = []
|
| 125 |
+
for frame_idx in frame_id_list:
|
| 126 |
+
try:
|
| 127 |
+
sampled_frames.append(frames[frame_idx])
|
| 128 |
+
except:
|
| 129 |
+
break
|
| 130 |
+
# Ensure the sampled list meets the required segment count
|
| 131 |
+
while len(sampled_frames) < num_segments:
|
| 132 |
+
sampled_frames.append(frames[last_frame_id])
|
| 133 |
+
return sampled_frames[:max_segments]
|
| 134 |
+
|
| 135 |
+
# Define embedder class for processing inputs and generating embeddings
|
| 136 |
+
class Qwen3VLEmbedder():
|
| 137 |
+
def __init__(
|
| 138 |
+
self,
|
| 139 |
+
model_name_or_path: str,
|
| 140 |
+
max_length: int = MAX_LENGTH,
|
| 141 |
+
min_pixels: int = MIN_PIXELS,
|
| 142 |
+
max_pixels: int = MAX_PIXELS,
|
| 143 |
+
total_pixels: int = MAX_TOTAL_PIXELS,
|
| 144 |
+
fps: float = FPS,
|
| 145 |
+
num_frames: int = MAX_FRAMES,
|
| 146 |
+
max_frames: int = MAX_FRAMES,
|
| 147 |
+
default_instruction: str = "Represent the user's input.",
|
| 148 |
+
**kwargs
|
| 149 |
+
):
|
| 150 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 151 |
+
|
| 152 |
+
self.max_length = max_length
|
| 153 |
+
self.min_pixels = min_pixels
|
| 154 |
+
self.max_pixels = max_pixels
|
| 155 |
+
self.total_pixels = total_pixels
|
| 156 |
+
self.fps = fps
|
| 157 |
+
self.num_frames = num_frames
|
| 158 |
+
self.max_frames = max_frames
|
| 159 |
+
|
| 160 |
+
self.default_instruction = default_instruction
|
| 161 |
+
|
| 162 |
+
self.model = Qwen3VLForEmbedding.from_pretrained(
|
| 163 |
+
model_name_or_path, trust_remote_code=True, **kwargs
|
| 164 |
+
).to(device)
|
| 165 |
+
self.processor = Qwen3VLProcessor.from_pretrained(
|
| 166 |
+
model_name_or_path, padding_side='right'
|
| 167 |
+
)
|
| 168 |
+
self.model.eval()
|
| 169 |
+
|
| 170 |
+
@torch.no_grad()
|
| 171 |
+
def forward(self, inputs: Dict[str, Any]) -> Dict[str, torch.Tensor]:
|
| 172 |
+
outputs = self.model(**inputs)
|
| 173 |
+
return {
|
| 174 |
+
'last_hidden_state': outputs.last_hidden_state,
|
| 175 |
+
'attention_mask': inputs.get('attention_mask')
|
| 176 |
+
}
|
| 177 |
+
|
| 178 |
+
# Truncate token sequence to a specified max length
|
| 179 |
+
def _truncate_tokens(self, token_ids: List[int], max_length: int) -> List[int]:
|
| 180 |
+
if len(token_ids) <= max_length:
|
| 181 |
+
return token_ids
|
| 182 |
+
|
| 183 |
+
special_token_ids = set(self.processor.tokenizer.all_special_ids)
|
| 184 |
+
num_special = sum(1 for token_idx in token_ids if token_idx in special_token_ids)
|
| 185 |
+
num_non_special_to_keep = max_length - num_special
|
| 186 |
+
|
| 187 |
+
final_token_ids = []
|
| 188 |
+
non_special_kept_count = 0
|
| 189 |
+
# Ensure retention of special tokens while truncating the rest
|
| 190 |
+
for token_idx in token_ids:
|
| 191 |
+
if token_idx in special_token_ids:
|
| 192 |
+
final_token_ids.append(token_idx)
|
| 193 |
+
elif non_special_kept_count < num_non_special_to_keep:
|
| 194 |
+
final_token_ids.append(token_idx)
|
| 195 |
+
non_special_kept_count += 1
|
| 196 |
+
return final_token_ids
|
| 197 |
+
|
| 198 |
+
# Format input based on provided text, image, video, and instruction
|
| 199 |
+
def format_model_input(
|
| 200 |
+
self, text: Optional[str] = None,
|
| 201 |
+
image: Optional[Union[str, Image.Image]] = None,
|
| 202 |
+
video: Optional[Union[str, List[Union[str, Image.Image]]]] = None,
|
| 203 |
+
instruction: Optional[str] = None,
|
| 204 |
+
fps: Optional[float] = None,
|
| 205 |
+
max_frames: Optional[int] = None
|
| 206 |
+
) -> List[Dict]:
|
| 207 |
+
|
| 208 |
+
# Ensure instruction ends with punctuation
|
| 209 |
+
if instruction:
|
| 210 |
+
instruction = instruction.strip()
|
| 211 |
+
if instruction and not unicodedata.category(instruction[-1]).startswith('P'):
|
| 212 |
+
instruction = instruction + '.'
|
| 213 |
+
|
| 214 |
+
# Initialize conversation with system prompts
|
| 215 |
+
content = []
|
| 216 |
+
conversation = [
|
| 217 |
+
{"role": "system", "content": [{"type": "text", "text": instruction or self.default_instruction}]},
|
| 218 |
+
{"role": "user", "content": content}
|
| 219 |
+
]
|
| 220 |
+
|
| 221 |
+
# Add text, image, or video content to conversation
|
| 222 |
+
if not text and not image and not video:
|
| 223 |
+
content.append({'type': 'text', 'text': "NULL"})
|
| 224 |
+
return conversation
|
| 225 |
+
|
| 226 |
+
if video:
|
| 227 |
+
video_content = None
|
| 228 |
+
video_kwargs = { 'total_pixels': self.total_pixels }
|
| 229 |
+
if isinstance(video, list):
|
| 230 |
+
video_content = video
|
| 231 |
+
if self.num_frames is not None or self.max_frames is not None:
|
| 232 |
+
video_content = sample_frames(video_content, self.num_frames, self.max_frames)
|
| 233 |
+
video_content = [
|
| 234 |
+
('file://' + ele if isinstance(ele, str) else ele)
|
| 235 |
+
for ele in video_content
|
| 236 |
+
]
|
| 237 |
+
elif isinstance(video, str):
|
| 238 |
+
video_content = video if video.startswith(('http://', 'https://')) else 'file://' + video
|
| 239 |
+
video_kwargs = {'fps': fps or self.fps, 'max_frames': max_frames or self.max_frames,}
|
| 240 |
+
else:
|
| 241 |
+
raise TypeError(f"Unrecognized video type: {type(video)}")
|
| 242 |
+
|
| 243 |
+
# Add video input details to content
|
| 244 |
+
if video_content:
|
| 245 |
+
content.append({
|
| 246 |
+
'type': 'video', 'video': video_content,
|
| 247 |
+
**video_kwargs
|
| 248 |
+
})
|
| 249 |
+
|
| 250 |
+
if image:
|
| 251 |
+
image_content = None
|
| 252 |
+
if isinstance(image, Image.Image):
|
| 253 |
+
image_content = image
|
| 254 |
+
elif isinstance(image, str):
|
| 255 |
+
image_content = image if image.startswith(('http', 'oss')) else 'file://' + image
|
| 256 |
+
else:
|
| 257 |
+
raise TypeError(f"Unrecognized image type: {type(image)}")
|
| 258 |
+
|
| 259 |
+
# Add image input details to content
|
| 260 |
+
if image_content:
|
| 261 |
+
content.append({
|
| 262 |
+
'type': 'image', 'image': image_content,
|
| 263 |
+
"min_pixels": self.min_pixels,
|
| 264 |
+
"max_pixels": self.max_pixels
|
| 265 |
+
})
|
| 266 |
+
|
| 267 |
+
if text:
|
| 268 |
+
content.append({'type': 'text', 'text': text})
|
| 269 |
+
|
| 270 |
+
return conversation
|
| 271 |
+
|
| 272 |
+
# Preprocess input conversations for model consumption
|
| 273 |
+
def _preprocess_inputs(self, conversations: List[List[Dict]]) -> Dict[str, torch.Tensor]:
|
| 274 |
+
text = self.processor.apply_chat_template(
|
| 275 |
+
conversations, add_generation_prompt=True, tokenize=False
|
| 276 |
+
)
|
| 277 |
+
|
| 278 |
+
try:
|
| 279 |
+
images, video_inputs, video_kwargs = process_vision_info(
|
| 280 |
+
conversations, image_patch_size=16,
|
| 281 |
+
return_video_metadata=True, return_video_kwargs=True
|
| 282 |
+
)
|
| 283 |
+
except Exception as e:
|
| 284 |
+
logger.error(f"Error in processing vision info: {e}")
|
| 285 |
+
images = None
|
| 286 |
+
video_inputs = None
|
| 287 |
+
video_kwargs = {'do_sample_frames': False}
|
| 288 |
+
text = self.processor.apply_chat_template(
|
| 289 |
+
[{'role': 'user', 'content': [{'type': 'text', 'text': 'NULL'}]}],
|
| 290 |
+
add_generation_prompt=True, tokenize=False
|
| 291 |
+
)
|
| 292 |
+
|
| 293 |
+
if video_inputs is not None:
|
| 294 |
+
videos, video_metadata = zip(*video_inputs)
|
| 295 |
+
videos = list(videos)
|
| 296 |
+
video_metadata = list(video_metadata)
|
| 297 |
+
else:
|
| 298 |
+
videos, video_metadata = None, None
|
| 299 |
+
|
| 300 |
+
inputs = self.processor(
|
| 301 |
+
text=text, images=images, videos=videos, video_metadata=video_metadata, truncation=True,
|
| 302 |
+
max_length=self.max_length, padding=True, do_resize=False, return_tensors='pt',
|
| 303 |
+
**video_kwargs
|
| 304 |
+
)
|
| 305 |
+
return inputs
|
| 306 |
+
|
| 307 |
+
# Pool the last hidden state by attention mask for embeddings
|
| 308 |
+
@staticmethod
|
| 309 |
+
def _pooling_last(hidden_state: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
|
| 310 |
+
flipped_tensor = attention_mask.flip(dims=[1])
|
| 311 |
+
last_one_positions = flipped_tensor.argmax(dim=1)
|
| 312 |
+
col = attention_mask.shape[1] - last_one_positions - 1
|
| 313 |
+
row = torch.arange(hidden_state.shape[0], device=hidden_state.device)
|
| 314 |
+
return hidden_state[row, col]
|
| 315 |
+
|
| 316 |
+
# Process inputs to generate normalized embeddings
|
| 317 |
+
def process(self, inputs: List[Dict[str, Any]], normalize: bool = True) -> tuple:
|
| 318 |
+
conversations = [self.format_model_input(
|
| 319 |
+
text=ele.get('text'),
|
| 320 |
+
image=ele.get('image'),
|
| 321 |
+
video=ele.get('video'),
|
| 322 |
+
instruction=ele.get('instruction'),
|
| 323 |
+
fps=ele.get('fps'),
|
| 324 |
+
max_frames=ele.get('max_frames')
|
| 325 |
+
) for ele in inputs]
|
| 326 |
+
|
| 327 |
+
processed_inputs = self._preprocess_inputs(conversations)
|
| 328 |
+
processed_inputs = {k: v.to(self.model.device) for k, v in processed_inputs.items()}
|
| 329 |
+
|
| 330 |
+
outputs = self.forward(processed_inputs)
|
| 331 |
+
embeddings = self._pooling_last(outputs['last_hidden_state'], outputs['attention_mask'])
|
| 332 |
+
|
| 333 |
+
# Normalize the embeddings if specified
|
| 334 |
+
if normalize:
|
| 335 |
+
embeddings = F.normalize(embeddings, p=2, dim=-1)
|
| 336 |
+
|
| 337 |
+
return embeddings
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
},
|
| 8 |
+
"image": {
|
| 9 |
+
"method": "forward",
|
| 10 |
+
"method_output_name": "last_hidden_state"
|
| 11 |
+
},
|
| 12 |
+
"video": {
|
| 13 |
+
"method": "forward",
|
| 14 |
+
"method_output_name": "last_hidden_state"
|
| 15 |
+
},
|
| 16 |
+
"message": {
|
| 17 |
+
"method": "forward",
|
| 18 |
+
"method_output_name": "last_hidden_state",
|
| 19 |
+
"format": "structured"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"module_output_name": "token_embeddings",
|
| 23 |
+
"processing_kwargs": {
|
| 24 |
+
"chat_template": {
|
| 25 |
+
"add_generation_prompt": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"unpad_inputs": false
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
|
| 3 |
+
size 11423705
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|