You can deploy this model and start earning money today!

RichardErkhov/
Qwen_-_Qwen2-Math-7B-Instruct-gguf

Name: Qwen_-_Qwen2-Math-7B-Instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2-Math-7B-Instruct - GGUF

Model creator: https://huggingface.co/Qwen/
Original model: https://huggingface.co/Qwen/Qwen2-Math-7B-Instruct/

Name	Quant method	Size
Qwen2-Math-7B-Instruct.Q2_K.gguf	Q2_K	2.81GB
Qwen2-Math-7B-Instruct.IQ3_XS.gguf	IQ3_XS	3.12GB
Qwen2-Math-7B-Instruct.IQ3_S.gguf	IQ3_S	3.26GB
Qwen2-Math-7B-Instruct.Q3_K_S.gguf	Q3_K_S	3.25GB
Qwen2-Math-7B-Instruct.IQ3_M.gguf	IQ3_M	3.33GB
Qwen2-Math-7B-Instruct.Q3_K.gguf	Q3_K	3.55GB
Qwen2-Math-7B-Instruct.Q3_K_M.gguf	Q3_K_M	3.55GB
Qwen2-Math-7B-Instruct.Q3_K_L.gguf	Q3_K_L	3.81GB
Qwen2-Math-7B-Instruct.IQ4_XS.gguf	IQ4_XS	3.96GB
Qwen2-Math-7B-Instruct.Q4_0.gguf	Q4_0	4.13GB
Qwen2-Math-7B-Instruct.IQ4_NL.gguf	IQ4_NL	4.16GB
Qwen2-Math-7B-Instruct.Q4_K_S.gguf	Q4_K_S	4.15GB
Qwen2-Math-7B-Instruct.Q4_K.gguf	Q4_K	4.36GB
Qwen2-Math-7B-Instruct.Q4_K_M.gguf	Q4_K_M	4.36GB
Qwen2-Math-7B-Instruct.Q4_1.gguf	Q4_1	4.54GB
Qwen2-Math-7B-Instruct.Q5_0.gguf	Q5_0	4.95GB
Qwen2-Math-7B-Instruct.Q5_K_S.gguf	Q5_K_S	4.95GB
Qwen2-Math-7B-Instruct.Q5_K.gguf	Q5_K	5.07GB
Qwen2-Math-7B-Instruct.Q5_K_M.gguf	Q5_K_M	5.07GB
Qwen2-Math-7B-Instruct.Q5_1.gguf	Q5_1	5.36GB
Qwen2-Math-7B-Instruct.Q6_K.gguf	Q6_K	5.82GB
Qwen2-Math-7B-Instruct.Q8_0.gguf	Q8_0	7.54GB

Original model description:

license: apache-2.0 language:

en pipeline_tag: text-generation tags:
chat

Qwen2-Math-7B-Instruct

[!Warning]

🚨 Temporarily this model mainly supports English. We will release bilingual (English & Chinese) models soon!

Introduction

Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus on their ability to solve arithmetic and mathematical problems. Today, we are delighted to introduce a serise of math-specific large language models of our Qwen2 series, Qwen2-Math and Qwen2-Math-Instruct-1.5B/7B/72B. Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o). We hope that Qwen2-Math can contribute to the scientific community for solving advanced mathematical problems that require complex, multi-step logical reasoning.

Model Details

For more details, please refer to our blog post and GitHub repo.

Requirements

transformers>=4.40.0 for Qwen2-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-Math-7B-Instruct is an instruction model for chatting;

Qwen2-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-Math can be deployed and inferred in the same way as Qwen2. 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-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 $4x+5 = 6x+7$."
messages = [
    {"role": "system", "content": "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(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]

🤖 ModelScope

We strongly advise users, especially those in mainland China, to use ModelScope. snapshot_download can help you solve issues concerning downloading checkpoints.

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}
}

RichardErkhov/Qwen_-_Qwen2-Math-7B-Instruct-gguf