初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX Source: Original Platform
This commit is contained in:
ModelHub XC
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
131
README.md
Normal file
131
README.md
Normal file
@@ -0,0 +1,131 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen2.5-VL-3B-Instruct
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- uncensored
|
||||||
|
- abliterated
|
||||||
|
- unfiltered
|
||||||
|
- unredacted
|
||||||
|
- vllm
|
||||||
|
- pytorch
|
||||||
|
- BF16
|
||||||
|
- max
|
||||||
|
- legal
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: image-text-to-text
|
||||||
|
library_name: transformers
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# **Qwen2.5-VL-3B-Instruct-Unredacted-MAX**
|
||||||
|
|
||||||
|
> **Qwen2.5-VL-3B-Instruct-Unredacted-MAX** is an optimized release built on top of **huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated**. This version focuses on **improved model packaging, updated compatibility with modern Transformers pipelines, and stable multimodal inference behavior**, while preserving the core vision-language reasoning capabilities of the original architecture. The result is a compact **3B vision-language model** designed for efficient deployment, research experimentation, and multimodal application development.
|
||||||
|
|
||||||
|
## Key Highlights
|
||||||
|
|
||||||
|
* **Optimized Release Packaging**
|
||||||
|
Streamlined repository structure for smoother loading, inference, and deployment workflows.
|
||||||
|
|
||||||
|
* **Modern Transformers Compatibility**
|
||||||
|
Updated to ensure stable integration with recent Hugging Face Transformers versions.
|
||||||
|
|
||||||
|
* **3B Vision-Language Architecture**
|
||||||
|
Built on **Qwen2.5-VL-3B-Instruct**, balancing multimodal capability with lightweight deployment requirements.
|
||||||
|
|
||||||
|
* **Stable Multimodal Inference**
|
||||||
|
Designed for consistent performance across image-text reasoning tasks.
|
||||||
|
|
||||||
|
* **Efficient Caption Generation**
|
||||||
|
Produces structured, descriptive outputs suitable for annotation and dataset building.
|
||||||
|
|
||||||
|
* **Dynamic Resolution Support**
|
||||||
|
Retains native handling of varying image resolutions and aspect ratios.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Base Model Signatures:
|
||||||
|
|
||||||
|
This model has been re-sharded and optimized for the latest Transformers version from the base model:
|
||||||
|
https://huggingface.co/huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Quick Start with Transformers
|
||||||
|
|
||||||
|
```python id="vl3b_code"
|
||||||
|
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
||||||
|
from qwen_vl_utils import process_vision_info
|
||||||
|
import torch
|
||||||
|
|
||||||
|
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
||||||
|
"prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX",
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
processor = AutoProcessor.from_pretrained(
|
||||||
|
"prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX"
|
||||||
|
)
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": [
|
||||||
|
{
|
||||||
|
"type": "image",
|
||||||
|
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
||||||
|
},
|
||||||
|
{"type": "text", "text": "Provide a detailed caption for this image."},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
text = processor.apply_chat_template(
|
||||||
|
messages, tokenize=False, add_generation_prompt=True
|
||||||
|
)
|
||||||
|
|
||||||
|
image_inputs, video_inputs = process_vision_info(messages)
|
||||||
|
|
||||||
|
inputs = processor(
|
||||||
|
text=[text],
|
||||||
|
images=image_inputs,
|
||||||
|
videos=video_inputs,
|
||||||
|
padding=True,
|
||||||
|
return_tensors="pt",
|
||||||
|
).to("cuda")
|
||||||
|
|
||||||
|
generated_ids = model.generate(**inputs, max_new_tokens=256)
|
||||||
|
|
||||||
|
output_text = processor.batch_decode(
|
||||||
|
[out[len(inp):] for inp, out in zip(inputs.input_ids, generated_ids)],
|
||||||
|
skip_special_tokens=True,
|
||||||
|
clean_up_tokenization_spaces=False
|
||||||
|
)
|
||||||
|
|
||||||
|
print(output_text)
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Intended Use
|
||||||
|
|
||||||
|
* Multimodal AI research and evaluation
|
||||||
|
* Image captioning and dataset generation pipelines
|
||||||
|
* Vision-language prototyping and experimentation
|
||||||
|
* Lightweight deployment in constrained environments
|
||||||
|
* Development of multimodal applications and tools
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Limitations & Risks
|
||||||
|
|
||||||
|
> **Important Note**: This model inherits behavior and constraints from its base architecture.
|
||||||
|
|
||||||
|
* Performance depends on image quality, resolution, and prompt design
|
||||||
|
* May produce incomplete or inaccurate interpretations in complex scenes
|
||||||
|
* Requires adequate GPU resources for stable inference
|
||||||
|
* Output consistency varies with decoding settings and runtime optimization
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
||||||
|
You are a helpful assistant.<|im_end|>
|
||||||
|
{% endif %}<|im_start|>{{ message['role'] }}
|
||||||
|
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
||||||
|
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
||||||
|
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
||||||
|
{% endif %}
|
||||||
138
config.json
Normal file
138
config.json
Normal file
@@ -0,0 +1,138 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"max_position_embeddings": 128000,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"text_config": {
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 128000,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2_5_vl_text",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
},
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"depth": 32,
|
||||||
|
"fullatt_block_indexes": [
|
||||||
|
7,
|
||||||
|
15,
|
||||||
|
23,
|
||||||
|
31
|
||||||
|
],
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1280,
|
||||||
|
"in_channels": 3,
|
||||||
|
"in_chans": 3,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3420,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"num_heads": 16,
|
||||||
|
"out_hidden_size": 2048,
|
||||||
|
"patch_size": 14,
|
||||||
|
"spatial_merge_size": 2,
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"tokens_per_second": 2,
|
||||||
|
"window_size": 112
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"repetition_penalty": 1.05,
|
||||||
|
"temperature": 1e-06,
|
||||||
|
"transformers_version": "4.57.6"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:33af97032c7220e910ceb8ac4572566eca7b70cc357d11dd73ace7f84dd8da93
|
||||||
|
size 7509338080
|
||||||
39
preprocessor_config.json
Normal file
39
preprocessor_config.json
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
{
|
||||||
|
"crop_size": null,
|
||||||
|
"data_format": "channels_first",
|
||||||
|
"default_to_square": true,
|
||||||
|
"device": null,
|
||||||
|
"disable_grouping": null,
|
||||||
|
"do_center_crop": null,
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_pad": null,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"input_data_format": null,
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"pad_size": null,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"return_tensors": null,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
43
video_preprocessor_config.json
Normal file
43
video_preprocessor_config.json
Normal file
@@ -0,0 +1,43 @@
|
|||||||
|
{
|
||||||
|
"crop_size": null,
|
||||||
|
"data_format": "channels_first",
|
||||||
|
"default_to_square": true,
|
||||||
|
"device": null,
|
||||||
|
"do_center_crop": null,
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"do_sample_frames": false,
|
||||||
|
"fps": null,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"input_data_format": null,
|
||||||
|
"max_frames": 768,
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_frames": 4,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"num_frames": null,
|
||||||
|
"pad_size": null,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"return_metadata": false,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"video_metadata": null,
|
||||||
|
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||||
|
}
|
||||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user