Welcome

HomeDashboardToolsStore
Use cases
PricingDocumentation

Welcome

Tools
Task History

deepseek-ai/ deepseek-math-7b-instruct

1981runs
0Comments

Prompt to send to the model.

Your request will cost $0.0006 per second.

Running this model on Wiro costs approximately $0.0318 in total.

(Total cost varies depending on the request’s execution time.)

There are no samples here… but why not take the plunge and experience it yourself? Dive in and make it yours!

1737531669 Report This Model


DeepSeek Chat


[🏠Homepage] | [🤖 Chat with DeepSeek LLM] | [Discord] | [Wechat(微信)]




Paper Link👁️














1. Introduction to DeepSeekMath


See the Introduction for more details.







2. How to Use


Here give some examples of how to use our model.


Chat Completion


❗❗❗ Please use chain-of-thought prompt to test DeepSeekMath-Instruct and DeepSeekMath-RL:



  • English questions: {question}\nPlease reason step by step, and put your final answer within \boxed{}.



  • Chinese questions: {question}\n请通过逐步推理来解答问题，并把最终答案放置于\boxed{}中。




import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "deepseek-ai/deepseek-math-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

messages = [
    {"role": "user", "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}."}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)

Avoiding the use of the provided function apply_chat_template, you can also interact with our model following the sample template. Note that messages should be replaced by your input.


User: {messages[0]['content']}

Assistant: {messages[1]['content']}<｜end▁of▁sentence｜>User: {messages[2]['content']}

Assistant:

Note: By default (add_special_tokens=True), our tokenizer automatically adds a bos_token (<｜begin▁of▁sentence｜>) before the input text. Additionally, since the system prompt is not compatible with this version of our models, we DO NOT RECOMMEND including the system prompt in your input.







3. License


This code repository is licensed under the MIT License. The use of DeepSeekMath models is subject to the Model License. DeepSeekMath supports commercial use.


See the LICENSE-MODEL for more details.







4. Contact


If you have any questions, please raise an issue or contact us at [email protected].


deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

DeepSeek-R1-Distill-Qwen-7B is a distilled version of the DeepSeek-R1 model with 7 billion parameters, designed to provide high-quality language understanding while optimizing efficiency. Leveraging advanced knowledge distillation techniques, it retains the core capabilities of larger models with improved speed and lower resource consumption. This model is well-suited for tasks requiring robust natural language processing while maintaining cost-effective deployment.
Run time: 1 second
2925 runs
0

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill-Qwen-32B is a distilled version of the DeepSeek-R1 model with 32 billion parameters, leveraging the Qwen architecture to deliver high-quality language understanding and generation. Through knowledge distillation, it retains the strengths of larger models while offering improved efficiency and reduced computational requirements. This model is ideal for large-scale AI applications that demand robust performance with optimized resource utilization.
Run time: 1 second
2888 runs
0

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

DeepSeek-R1-Distill-Qwen-14B is a distilled version of the DeepSeek-R1 model, featuring 14 billion parameters. Built on the Qwen architecture, it utilizes advanced knowledge distillation techniques to achieve a balance between high performance and computational efficiency. This model is well-suited for a wide range of natural language processing tasks, providing accurate and context-aware responses while optimizing resource consumption for deployment in production environments.
Run time: 1 second
0 runs
0

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

DeepSeek-R1-Distill-Llama-8B is a distilled version of the DeepSeek-R1 model based on the LLaMA architecture, featuring 8 billion parameters. It offers a balance between performance and efficiency by leveraging knowledge distillation techniques to reduce computational costs while maintaining high-quality language processing capabilities. This model is ideal for applications that require powerful text generation and understanding with optimized resource usage.
Run time: 1 second
1812 runs
0

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

DeepSeek-R1-Distill-Qwen-1.5B is a distilled version of the DeepSeek-R1 model, designed to offer a balance between efficiency and performance. With 1.5 billion parameters, it leverages knowledge distillation techniques to retain the capabilities of larger models while optimizing for faster inference and reduced resource consumption. Ideal for applications requiring high-quality language understanding with lower computational overhead.
Run time: 1 second
2610 runs
0

deepseek-ai/deepseek-math-7b-instruct

deepseek-ai/deepseek-math-7b-instruct is a 7 billion parameter AI model specifically designed to excel in mathematical reasoning and problem-solving tasks, providing accurate and detailed step-by-step solutions.
Run time: 1 second
1508 runs
0

Select Language