You can deploy this model and start earning money today!

RichardErkhov/
Qwen_-_Qwen2.5-Math-1.5B-Instruct-gguf

Name: Qwen_-_Qwen2.5-Math-1.5B-Instruct-gguf
Rating: 2.5 (2336 reviews)

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2.5-Math-1.5B-Instruct - GGUF

Model creator: https://huggingface.co/Qwen/
Original model: https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct/

Name	Quant method	Size
Qwen2.5-Math-1.5B-Instruct.Q2_K.gguf	Q2_K	0.63GB
Qwen2.5-Math-1.5B-Instruct.IQ3_XS.gguf	IQ3_XS	0.68GB
Qwen2.5-Math-1.5B-Instruct.IQ3_S.gguf	IQ3_S	0.71GB
Qwen2.5-Math-1.5B-Instruct.Q3_K_S.gguf	Q3_K_S	0.71GB
Qwen2.5-Math-1.5B-Instruct.IQ3_M.gguf	IQ3_M	0.72GB
Qwen2.5-Math-1.5B-Instruct.Q3_K.gguf	Q3_K	0.77GB
Qwen2.5-Math-1.5B-Instruct.Q3_K_M.gguf	Q3_K_M	0.77GB
Qwen2.5-Math-1.5B-Instruct.Q3_K_L.gguf	Q3_K_L	0.82GB
Qwen2.5-Math-1.5B-Instruct.IQ4_XS.gguf	IQ4_XS	0.84GB
Qwen2.5-Math-1.5B-Instruct.Q4_0.gguf	Q4_0	0.87GB
Qwen2.5-Math-1.5B-Instruct.IQ4_NL.gguf	IQ4_NL	0.88GB
Qwen2.5-Math-1.5B-Instruct.Q4_K_S.gguf	Q4_K_S	0.88GB
Qwen2.5-Math-1.5B-Instruct.Q4_K.gguf	Q4_K	0.92GB
Qwen2.5-Math-1.5B-Instruct.Q4_K_M.gguf	Q4_K_M	0.92GB
Qwen2.5-Math-1.5B-Instruct.Q4_1.gguf	Q4_1	0.95GB
Qwen2.5-Math-1.5B-Instruct.Q5_0.gguf	Q5_0	1.02GB
Qwen2.5-Math-1.5B-Instruct.Q5_K_S.gguf	Q5_K_S	1.02GB
Qwen2.5-Math-1.5B-Instruct.Q5_K.gguf	Q5_K	1.05GB
Qwen2.5-Math-1.5B-Instruct.Q5_K_M.gguf	Q5_K_M	1.05GB
Qwen2.5-Math-1.5B-Instruct.Q5_1.gguf	Q5_1	1.1GB
Qwen2.5-Math-1.5B-Instruct.Q6_K.gguf	Q6_K	1.19GB
Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf	Q8_0	1.53GB

Original model description:

base_model: Qwen/Qwen2.5-Math-1.5B language:

en pipeline_tag: text-generation tags:
chat library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct/blob/main/LICENSE

Qwen2.5-Math-1.5B-Instruct

[!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 - 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.

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 and GitHub repo.

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.

Quick Start

[!Important]

Qwen2.5-Math-1.5B-Instruct is an instruction model for chatting;

Qwen2.5-Math-1.5B 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. 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-1.5B-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{yang2024qwen25mathtechnicalreportmathematical,
  title={Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement}, 
  author={An Yang and Beichen Zhang and Binyuan Hui and Bofei Gao and Bowen Yu and Chengpeng Li and Dayiheng Liu and Jianhong Tu and Jingren Zhou and Junyang Lin and Keming Lu and Mingfeng Xue and Runji Lin and Tianyu Liu and Xingzhang Ren and Zhenru Zhang},
  journal={arXiv preprint arXiv:2409.12122},
  year={2024}
}

RichardErkhov/Qwen_-_Qwen2.5-Math-1.5B-Instruct-gguf