初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/Qwen2.5-Math-7B-Instruct-GGUF
Source: Original Platform

.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-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-Math-7B-Instruct.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a06e837a82e55039e83a3d822972e43f4f7283bc57b470706b7d4099c4c999
+size 3015940416

Qwen2.5-Math-7B-Instruct.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830c4f058eb3e7b1bfe1953289a62460ba501db3cfbdec7d07734377d054c3b5
+size 4088459584

Qwen2.5-Math-7B-Instruct.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef59b7c343fe85014749c7061517a884c9128934efdddf0254cad37c973c8fe
+size 3808391488

Qwen2.5-Math-7B-Instruct.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e04830ee76cea6583f2d5428b3ae15cdc2a9e641ae4c69b252194536e9865f1
+size 3492368704

Qwen2.5-Math-7B-Instruct.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb55e0a0094f0918b3fc7ca5b549cec6066d6cde42065d5e6ff532b43cd5174
+size 4431391040

Qwen2.5-Math-7B-Instruct.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5362908736e13fa22b2766761549e26f6833f2465e685b44925517284874f1
+size 4873283904

Qwen2.5-Math-7B-Instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90c4146d735bcbc09213c6854292651a18444163d13d330e2dad9f49b6e0fe0
+size 4683073856

Qwen2.5-Math-7B-Instruct.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2f1745ed53004bcd573d87232776aed5a1a83e026ce4f7461eeed2f1276881
+size 4457769280

Qwen2.5-Math-7B-Instruct.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb1dbf209d3969f17aa733062665df7ae3d52ca99bc20954616f4119937c2f6
+size 5315176768

Qwen2.5-Math-7B-Instruct.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4174bcfade619589802cf8d2b2610a9106f52a4c132fea78b812d5f0083cdc9
+size 5757069632

Qwen2.5-Math-7B-Instruct.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7466d8c83cfd23a6b540aa2862f69ab5aa5704526d213482b515d652e12a04
+size 5444831552

Qwen2.5-Math-7B-Instruct.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adebb7476639f6e98d065d9eb73271f61f1ecde96b54c4b3a1f50a66882fcb15
+size 5315176768

Qwen2.5-Math-7B-Instruct.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c30575b539f58a19890df07b91701a25df2172dd3deebc9e865c4ecaf88d941
+size 6254199104

Qwen2.5-Math-7B-Instruct.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841398140d68be83394161a195bd4bad57f830280563de94f0afa8cde01c4aa4
+size 8098525504

README.md

@@ -0,0 +1,132 @@
+
+---
+
+base_model: Qwen/Qwen2.5-Math-7B
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/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-Instruct-GGUF
+This is quantized version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) created using llama.cpp
+
+# Original Model Card
+
+
+
+# Qwen2.5-Math-7B-Instruct
+
+> [!Warning]
+> <div align="center">
+> <b>
+> 🚨 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.
+> </b>
+> </div>
+
+## 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]
+> <div align="center">
+> <b>
+> 🚨 This is a must because <code>transformers</code> integrated Qwen2 codes since <code>4.37.0</code>.
+> </b>
+> </div>
+
+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.
+> 
+
+### 🤗 Hugging Face Transformers
+
+Qwen2.5-Math can be deployed and infered in the same way as [Qwen2.5](https://github.com/QwenLM/Qwen2.5). Here we show a code snippet to show you how to use the chat model with `transformers`:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen2.5-Math-7B-Instruct"
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
+
+# CoT
+messages = [
+    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
+    {"role": "user", "content": prompt}
+]
+
+# TIR
+messages = [
+    {"role": "system", "content": "Please integrate natural language reasoning with programs to solve the problem above, and put your final answer within \\boxed{}."},
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(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]
+```
+
+## 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}
+}
+```

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}