commit 869c63e5f8323436b19a80f39ede8ad3a02ded8c Author: ModelHub XC Date: Tue Sep 15 12:10:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/Qwen2.5-Math-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7fe619 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-Math-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-7B.Q2_K.gguf b/Qwen2.5-Math-7B.Q2_K.gguf new file mode 100644 index 0000000..075ccc4 --- /dev/null +++ b/Qwen2.5-Math-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c20acf95bcf47ab840990273966c2077aa10e6c8e8473b93c47e40db35e9be1 +size 3015940416 diff --git a/Qwen2.5-Math-7B.Q3_K_L.gguf b/Qwen2.5-Math-7B.Q3_K_L.gguf new file mode 100644 index 0000000..cfd2f68 --- /dev/null +++ b/Qwen2.5-Math-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ef6a15c62fbc5813fc8c4d4f7709355e224a77b4fa2ddaff8e0896684c5843 +size 4088459584 diff --git a/Qwen2.5-Math-7B.Q3_K_M.gguf b/Qwen2.5-Math-7B.Q3_K_M.gguf new file mode 100644 index 0000000..4f598c0 --- /dev/null +++ b/Qwen2.5-Math-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ae508b783dac682d51aa8c00f9a439a9237ca3d3e69d65c7d6120ba0cce3c3 +size 3808391488 diff --git a/Qwen2.5-Math-7B.Q3_K_S.gguf b/Qwen2.5-Math-7B.Q3_K_S.gguf new file mode 100644 index 0000000..e696d79 --- /dev/null +++ b/Qwen2.5-Math-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebf1f71208c9c42fdf5fca61b36efe9a7670d6e67632d068224b5f0715bab45 +size 3492368704 diff --git a/Qwen2.5-Math-7B.Q4_0.gguf b/Qwen2.5-Math-7B.Q4_0.gguf new file mode 100644 index 0000000..df4b0da --- /dev/null +++ b/Qwen2.5-Math-7B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ace812f0526e54a3a6c0547558c3678f31db4c899fbe00b6760dab5d07697be +size 4431391040 diff --git a/Qwen2.5-Math-7B.Q4_1.gguf b/Qwen2.5-Math-7B.Q4_1.gguf new file mode 100644 index 0000000..de7d6e1 --- /dev/null +++ b/Qwen2.5-Math-7B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b1c7ceb34e85af78b00bfe01e29ea151c9aa1b09407866fa04da11d49716dd +size 4873283904 diff --git a/Qwen2.5-Math-7B.Q4_K_M.gguf b/Qwen2.5-Math-7B.Q4_K_M.gguf new file mode 100644 index 0000000..0c7dadd --- /dev/null +++ b/Qwen2.5-Math-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3833899ed73c724ee13123c2f83608ee54b84846e5f6a3c29136bde9a89d4090 +size 4683073856 diff --git a/Qwen2.5-Math-7B.Q4_K_S.gguf b/Qwen2.5-Math-7B.Q4_K_S.gguf new file mode 100644 index 0000000..51b0897 --- /dev/null +++ b/Qwen2.5-Math-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b4be66cb58b6ef20760a3c34372c18bc9b6011cf6e34acdf3d01cb5fd62585 +size 4457769280 diff --git a/Qwen2.5-Math-7B.Q5_0.gguf b/Qwen2.5-Math-7B.Q5_0.gguf new file mode 100644 index 0000000..744a4ba --- /dev/null +++ b/Qwen2.5-Math-7B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdc4bba0fe452cd881eb75892de4ae2b7dd853666bc57ab6ad475ad8b599983 +size 5315176768 diff --git a/Qwen2.5-Math-7B.Q5_1.gguf b/Qwen2.5-Math-7B.Q5_1.gguf new file mode 100644 index 0000000..4717b09 --- /dev/null +++ b/Qwen2.5-Math-7B.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970f4a5a7dfa78dc423bb945faec938c3cbe5b354535c84f446f25d3dd04dac3 +size 5757069632 diff --git a/Qwen2.5-Math-7B.Q5_K_M.gguf b/Qwen2.5-Math-7B.Q5_K_M.gguf new file mode 100644 index 0000000..9ae7998 --- /dev/null +++ b/Qwen2.5-Math-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bbca66facf3bd9f89a3c0f2f00a02a9d1bef3f9d12d91e4b3e9a75906f3460 +size 5444831552 diff --git a/Qwen2.5-Math-7B.Q5_K_S.gguf b/Qwen2.5-Math-7B.Q5_K_S.gguf new file mode 100644 index 0000000..678bb00 --- /dev/null +++ b/Qwen2.5-Math-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c513b39b215f706832b1e0eaaa5efb3aab371236fd93d27f84c83bee569ff6d +size 5315176768 diff --git a/Qwen2.5-Math-7B.Q6_K.gguf b/Qwen2.5-Math-7B.Q6_K.gguf new file mode 100644 index 0000000..63a08cd --- /dev/null +++ b/Qwen2.5-Math-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1b61fc8769bdf2e60fdf88f5c261229c1cf552bbee4662adb13787ddd1adbc +size 6254199104 diff --git a/Qwen2.5-Math-7B.Q8_0.gguf b/Qwen2.5-Math-7B.Q8_0.gguf new file mode 100644 index 0000000..d0eafb9 --- /dev/null +++ b/Qwen2.5-Math-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5ba6dd962813200feb50a5c97ff11c19c85e9e3860752937a1218561ee9c34 +size 8098525504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..64489aa --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ + +--- + +base_model: Qwen/Qwen2.5-7B +language: +- en +pipeline_tag: text-generation +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Math-7B/blob/main/LICENSE + +--- + +[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) + + +# QuantFactory/Qwen2.5-Math-7B-GGUF +This is quantized version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) created using llama.cpp + +# Original Model Card + + + +# Qwen2.5-Math-7B + +> [!Warning] +>
+> +> 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. +> +>
+ +## Introduction + +In August 2024, we released the first series of mathematical LLMs - [Qwen2-Math](https://qwenlm.github.io/blog/qwen2-math/) - of our Qwen family. A month later, we have upgraded it and open-sourced **Qwen2.5-Math** series, including base models **Qwen2.5-Math-1.5B/7B/72B**, instruction-tuned models **Qwen2.5-Math-1.5B/7B/72B-Instruct**, and mathematical reward model **Qwen2.5-Math-RM-72B**. + +Unlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT. + +![](http://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2.5/qwen2.5-math-pipeline.jpeg) + +While CoT plays a vital role in enhancing the reasoning capabilities of LLMs, it faces challenges in achieving computational accuracy and handling complex mathematical or algorithmic reasoning tasks, such as finding the roots of a quadratic equation or computing the eigenvalues of a matrix. TIR can further improve the model's proficiency in precise computation, symbolic manipulation, and algorithmic manipulation. Qwen2.5-Math-1.5B/7B/72B-Instruct achieve 79.7, 85.3, and 87.8 respectively on the MATH benchmark using TIR. + +## Model Details + + +For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen2.5-math/) and [GitHub repo](https://github.com/QwenLM/Qwen2.5-Math). + + +## Requirements +* `transformers>=4.37.0` for Qwen2.5-Math models. The latest version is recommended. + +> [!Warning] +>
+> +> 🚨 This is a must because transformers integrated Qwen2 codes since 4.37.0. +> +>
+ +For requirements on GPU memory and the respective throughput, see similar results of Qwen2 [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). + +## Quick Start + +> [!Important] +> +> **Qwen2.5-Math-7B-Instruct** is an instruction model for chatting; +> +> **Qwen2.5-Math-7B** is a base model typically used for completion and few-shot inference, serving as a better starting point for fine-tuning. +> + +## Citation + +If you find our work helpful, feel free to give us a citation. + +``` +@article{yang2024qwen2, + title={Qwen2 technical report}, + author={Yang, An and Yang, Baosong and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Zhou, Chang and Li, Chengpeng and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and others}, + journal={arXiv preprint arXiv:2407.10671}, + year={2024} +} +``` diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file