初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/JSONify-Flux Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
127
README.md
Normal file
127
README.md
Normal file
@@ -0,0 +1,127 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
base_model:
|
||||
- Qwen/Qwen2-VL-2B-Instruct
|
||||
pipeline_tag: image-text-to-text
|
||||
library_name: transformers
|
||||
tags:
|
||||
- caption
|
||||
- text-generation-inference
|
||||
- flux
|
||||
---
|
||||
|
||||
|
||||
# **JSONify-Flux**
|
||||
|
||||
The **JSONify-Flux** model is a fine-tuned version of Qwen2-VL, specifically tailored for **Flux-generated image analysis**, **caption extraction**, and **structured JSON formatting**. This model is optimized for tasks involving **image-to-text conversion**, **Optical Character Recognition (OCR)**, and **context-aware structured data extraction**.
|
||||
|
||||
#### Key Enhancements:
|
||||
|
||||
* **Advanced Image Understanding**: JSONify-Flux has been trained using **30 million trainable parameters** on **Flux-generated images and their captions**, ensuring precise image comprehension.
|
||||
|
||||
* **Optimized for JSON Output**: The model is designed to output structured JSON data, making it suitable for integration with databases, APIs, and automation pipelines.
|
||||
|
||||
* **Enhanced OCR Capabilities**: JSONify-Flux excels in recognizing and extracting text from images with a high degree of accuracy.
|
||||
|
||||
* **Multimodal Processing**: Supports both image and text inputs while generating structured JSON-formatted outputs.
|
||||
|
||||
* **Multilingual Support**: Trained to recognize text inside images in multiple languages, including English, Chinese, European languages, Japanese, Korean, Arabic, and more.
|
||||
|
||||
### How to Use
|
||||
|
||||
```python
|
||||
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
||||
from qwen_vl_utils import process_vision_info
|
||||
|
||||
# Load the model with optimized parameters
|
||||
model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||
"prithivMLmods/JSONify-Flux", torch_dtype="auto", device_map="auto"
|
||||
)
|
||||
|
||||
# Recommended acceleration for performance optimization
|
||||
# model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||
# "prithivMLmods/JSONify-Flux",
|
||||
# torch_dtype=torch.bfloat16,
|
||||
# attn_implementation="flash_attention_2",
|
||||
# device_map="auto",
|
||||
# )
|
||||
|
||||
# Default processor
|
||||
processor = AutoProcessor.from_pretrained("prithivMLmods/JSONify-Flux")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "image",
|
||||
"image": "https://flux-generated.com/sample_image.jpeg",
|
||||
},
|
||||
{"type": "text", "text": "Extract structured information from this image in JSON format."},
|
||||
],
|
||||
}
|
||||
]
|
||||
|
||||
# Prepare for inference
|
||||
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",
|
||||
)
|
||||
inputs = inputs.to("cuda")
|
||||
|
||||
# Generate output
|
||||
generated_ids = model.generate(**inputs, max_new_tokens=256)
|
||||
generated_ids_trimmed = [
|
||||
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
||||
]
|
||||
output_text = processor.batch_decode(
|
||||
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
)
|
||||
print(output_text)
|
||||
```
|
||||
|
||||
### JSON Output Example:
|
||||
```json
|
||||
{
|
||||
"image_id": "sample_image.jpeg",
|
||||
"captions": [
|
||||
"A futuristic cityscape with neon lights.",
|
||||
"A digital artwork featuring an abstract environment."
|
||||
],
|
||||
"recognized_text": "Welcome to Flux City!",
|
||||
"metadata": {
|
||||
"color_palette": ["#FF5733", "#33FF57", "#3357FF"],
|
||||
"detected_objects": ["building", "sign", "street light"]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### **Key Features**
|
||||
|
||||
1. **Flux-Based Training Data**
|
||||
- Trained using **Flux-generated images** and captions to ensure high-quality structured output.
|
||||
|
||||
2. **Optical Character Recognition (OCR)**
|
||||
- Extracts and processes textual content within images.
|
||||
|
||||
3. **Structured JSON Output**
|
||||
- Outputs information in **JSON format** for easy integration with various applications.
|
||||
|
||||
4. **Conversational Capabilities**
|
||||
- Handles **multi-turn interactions** with structured responses.
|
||||
|
||||
5. **Image & Text Processing**
|
||||
- Inputs can include **images, text, or both**, with JSON-formatted results.
|
||||
|
||||
6. **Secure and Optimized Model Weights**
|
||||
- Uses **Safetensors** for enhanced security and efficient model loading.
|
||||
16
added_tokens.json
Normal file
16
added_tokens.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
50
config.json
Normal file
50
config.json
Normal file
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"_name_or_path": "prithivMLmods/JSONify-Flux",
|
||||
"architectures": [
|
||||
"Qwen2VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_vl",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151654,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"hidden_size": 1536,
|
||||
"in_chans": 3,
|
||||
"model_type": "qwen2_vl",
|
||||
"spatial_patch_size": 14,
|
||||
"torch_dtype": "bfloat16"
|
||||
},
|
||||
"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}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 32768,
|
||||
"pad_token_id": 151654,
|
||||
"temperature": 0.01,
|
||||
"top_k": 1,
|
||||
"top_p": 0.001,
|
||||
"transformers_version": "4.48.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5d3a311cf59a24d1b50f9bf16d33fb7d2e4f0d09082e2a4ebbf57b2daddfc34
|
||||
size 4418050848
|
||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"max_pixels": 12845056,
|
||||
"min_pixels": 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": "<|vision_pad|>",
|
||||
"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 sha256:948c45c29a91dd2e6ae77d6f5a324a3d408bcca6ad443365b2e79986f1422771
|
||||
size 11420540
|
||||
145
tokenizer_config.json
Normal file
145
tokenizer_config.json
Normal file
@@ -0,0 +1,145 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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,
|
||||
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "right",
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user