初始化项目，由ModelHub XC社区提供模型

Model: Mungert/Qwen2.5-14B-Instruct-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,61 @@
+*.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
+Qwen2.5-14B-Instruct-f16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-bf16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-f16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-bf16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-14B-Instruct-f16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-14B-Instruct-bf16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5fb82e5752927773538ca4ff5fc057b66b13eb6bdba12394dcef81996e1dcd0
+size 11025768480

Qwen2.5-14B-Instruct-bf16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcdd71a6322fdae2390683ad35b6695edc6f7c0185f78bb5d8a12db55ad3956
+size 13961617440

Qwen2.5-14B-Instruct-bf16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bfe99204d906d0deda1b2fd24a831282a8b20bfb31b0146f0eb75558588133
+size 17161412352

Qwen2.5-14B-Instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6c974a5f1b721e4dcd31c8900accf08518d32c16f7e6654c0190bbcdff97e7
+size 29547716352

Qwen2.5-14B-Instruct-f16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59cd7e3190daa80fa40302c82f2e3250c55ed3aadb7f9bc4ae64f75bb4a4528
+size 11025768480

Qwen2.5-14B-Instruct-f16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7beb4de1a91946ef1d893fcc54f90d8ccc10a9c1c30ee49758a935ea49effc74
+size 13961617440

Qwen2.5-14B-Instruct-f16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03287950736c2e6ea175145d1b1f9ddc2a437fd0c7d78ac775012c88f52c38d
+size 17161412352

Qwen2.5-14B-Instruct-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b2db424ef8b9bc650021c8ff729b85be2f58ba43449f85ef2cee1f692e04ba
+size 6383362080

Qwen2.5-14B-Instruct-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce97b851290eab04267f0d16f5bd30008f24dcd8f3cd4842883545e0cf6c719
+size 8549183520

Qwen2.5-14B-Instruct-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea4266a0f30b89915af1472a014d3bdaf8cc72846d4f85c5a7cd8424f8a0a61
+size 8119840800

Qwen2.5-14B-Instruct-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c548ea43b7500f562e757635dcc1ca9de46ba6115ab21308fef83b04fad77820
+size 7339204640

Qwen2.5-14B-Instruct-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44368d0e53588a79cf36be82a29cbc8beef724004fc4304ec8e617f4f0b26c3
+size 6659596320

Qwen2.5-14B-Instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c51095534554571acd0888c3d4766ca938f1a1379ef0f6eec4729b874d58172
+size 9095569440

Qwen2.5-14B-Instruct-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971cf9696cd6dad8cb3c4e1bf63db28a1f843a1868acb46931fbbc65524aee0c
+size 9921323040

Qwen2.5-14B-Instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acd0b6d7662229cb97ef5465374dba7ff2da30723e67da5ef39048a6eb530f6
+size 8988110880

Qwen2.5-14B-Instruct-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6691f8adaa1914e1e113b461f5a780a6db7868505cda86e877413dd91a55ebe
+size 8573431840

Qwen2.5-14B-Instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec505b8ba313c7d791afadc3c2292a06dd52449cb98668c4794624d7bc14e71
+size 10508873760

Qwen2.5-14B-Instruct-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdd56737913b24155d0440e9c0c1d54a8fa4808b1ae40167816b806eddb2fe3
+size 10266554400

Qwen2.5-14B-Instruct-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa538062c7921a5ff1dc247ec97179c437db684129d434a9593bcdcd4fdadd1f
+size 12124684320

Qwen2.5-14B-Instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7566ce125ac78cf700920f14dd31708a990d6e6dc9f0217d85b98ab4d764fec6
+size 15701597952

Qwen2.5-14B-Instruct.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd865d5a17dca9227532c7141f3ca8d5230a024ae901e09fd5bb22a5f43b7f6
+size 8563610

README.md

@@ -0,0 +1,266 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-14B
+tags:
+- chat
+library_name: transformers
+---
+
+# <span style="color: #7FFF7F;">Qwen2.5-14B-Instruct GGUF Models</span>
+
+## **Choosing the Right Model Format**  
+
+Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
+
+### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
+- A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
+- Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
+- Recommended if your hardware supports **BF16 acceleration** (check your device’s specs).  
+- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
+
+📌 **Use BF16 if:**  
+✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
+✔ You want **higher precision** while saving memory.  
+✔ You plan to **requantize** the model into another format.  
+
+📌 **Avoid BF16 if:**  
+❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
+❌ You need compatibility with older devices that lack BF16 optimization.  
+
+---
+
+### **F16 (Float 16) – More widely supported than BF16**  
+- A 16-bit floating-point **high precision** but with less of range of values than BF16. 
+- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
+- Slightly lower numerical precision than BF16 but generally sufficient for inference.  
+
+📌 **Use F16 if:**  
+✔ Your hardware supports **FP16** but **not BF16**.  
+✔ You need a **balance between speed, memory usage, and accuracy**.  
+✔ You are running on a **GPU** or another device optimized for FP16 computations.  
+
+📌 **Avoid F16 if:**  
+❌ Your device lacks **native FP16 support** (it may run slower than expected).  
+❌ You have memory limitations.  
+
+---
+
+### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
+Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
+- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
+- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
+
+📌 **Use Quantized Models if:**  
+✔ You are running inference on a **CPU** and need an optimized model.  
+✔ Your device has **low VRAM** and cannot load full-precision models.  
+✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
+
+📌 **Avoid Quantized Models if:**  
+❌ You need **maximum accuracy** (full-precision models are better for this).  
+❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
+
+---
+
+### **Summary Table: Model Format Selection**  
+
+| Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
+|--------------|------------|---------------|----------------------|---------------|  
+| **BF16**     | Highest       | High      | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
+| **F16**      | High     | High           | FP16-supported devices | GPU inference when BF16 isn’t available |  
+| **Q4_K**     | Low        | Very Low      | CPU or Low-VRAM devices | Best for memory-constrained environments |  
+| **Q6_K**     | Medium Low     | Low      | CPU with more memory | Better accuracy while still being quantized |  
+| **Q8**       | Medium       | Moderate        | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
+
+
+## **Included Files & Details**  
+
+### `Qwen2.5-14B-Instruct-bf16.gguf`  
+- Model weights preserved in **BF16**.  
+- Use this if you want to **requantize** the model into a different format.  
+- Best if your device supports **BF16 acceleration**.  
+
+### `Qwen2.5-14B-Instruct-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `Qwen2.5-14B-Instruct-bf16-q8_0.gguf`  
+- **Output & embeddings** remain in **BF16**.  
+- All other layers quantized to **Q8_0**.  
+- Use if your device supports **BF16** and you want a quantized version.  
+
+### `Qwen2.5-14B-Instruct-f16-q8_0.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `Qwen2.5-14B-Instruct-q4_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `Qwen2.5-14B-Instruct-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `Qwen2.5-14B-Instruct-q6_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+
+### `Qwen2.5-14B-Instruct-q8_0.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com).
+
+💬 Click the **chat icon** (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.
+
+### What I'm Testing
+
+I'm experimenting with **function calling** against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function".
+
+🟡 **TestLLM** – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .
+
+### The other Available AI Assistants
+
+🟢 **TurboLLM** – Uses **gpt-4o-mini** Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .
+
+🔵 **HugLLM** – Runs **open-source Hugging Face models** Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊
+
+
+
+# Qwen2.5-14B-Instruct
+
+## Introduction
+
+Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
+
+- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
+- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
+- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
+- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. 
+
+**This repo contains the instruction-tuned 14B Qwen2.5 model**, which has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
+- Number of Parameters: 14.7B
+- Number of Paramaters (Non-Embedding): 13.1B
+- Number of Layers: 48
+- Number of Attention Heads (GQA): 40 for Q and 8 for KV
+- Context Length: Full 131,072 tokens and generation 8192 tokens
+  - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.
+
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## Requirements
+
+The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.37.0`, you will encounter the following error:
+```
+KeyError: 'qwen2'
+```
+
+## Quickstart
+
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen2.5-14B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+
+### Processing Long Texts
+
+The current `config.json` is set for context length up to 32,768 tokens.
+To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
+
+For supported frameworks, you could add the following to `config.json` to enable YaRN:
+```json
+{
+  ...,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "type": "yarn"
+  }
+}
+```
+
+For deployment, we recommend using vLLM. 
+Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM.
+Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**. 
+We advise adding the `rope_scaling` configuration only when processing long contexts is required.
+
+## Evaluation & Performance
+
+Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
+
+For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen2.5,
+    title = {Qwen2.5: A Party of Foundation Models},
+    url = {https://qwenlm.github.io/blog/qwen2.5/},
+    author = {Qwen Team},
+    month = {September},
+    year = {2024}
+}
+
+@article{qwen2,
+      title={Qwen2 Technical Report}, 
+      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
+      journal={arXiv preprint arXiv:2407.10671},
+      year={2024}
+}
+```