blockblockblock / deepseek-math-7b-rl-bpw5

huggingface.co
Total runs: 23
24-hour runs: 0
7-day runs: 2
30-day runs: 16
Model's Last Updated: April 17 2024
text-generation

Introduction of deepseek-math-7b-rl-bpw5

Model Details of deepseek-math-7b-rl-bpw5

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] .

Runs of blockblockblock deepseek-math-7b-rl-bpw5 on huggingface.co

23
Total runs
0
24-hour runs
1
3-day runs
2
7-day runs
16
30-day runs

More Information About deepseek-math-7b-rl-bpw5 huggingface.co Model

More deepseek-math-7b-rl-bpw5 license Visit here:

https://choosealicense.com/licenses/deepseek

deepseek-math-7b-rl-bpw5 huggingface.co

deepseek-math-7b-rl-bpw5 huggingface.co is an AI model on huggingface.co that provides deepseek-math-7b-rl-bpw5's model effect (), which can be used instantly with this blockblockblock deepseek-math-7b-rl-bpw5 model. huggingface.co supports a free trial of the deepseek-math-7b-rl-bpw5 model, and also provides paid use of the deepseek-math-7b-rl-bpw5. Support call deepseek-math-7b-rl-bpw5 model through api, including Node.js, Python, http.

blockblockblock deepseek-math-7b-rl-bpw5 online free

deepseek-math-7b-rl-bpw5 huggingface.co is an online trial and call api platform, which integrates deepseek-math-7b-rl-bpw5's modeling effects, including api services, and provides a free online trial of deepseek-math-7b-rl-bpw5, you can try deepseek-math-7b-rl-bpw5 online for free by clicking the link below.

blockblockblock deepseek-math-7b-rl-bpw5 online free url in huggingface.co:

https://huggingface.co/blockblockblock/deepseek-math-7b-rl-bpw5

deepseek-math-7b-rl-bpw5 install

deepseek-math-7b-rl-bpw5 is an open source model from GitHub that offers a free installation service, and any user can find deepseek-math-7b-rl-bpw5 on GitHub to install. At the same time, huggingface.co provides the effect of deepseek-math-7b-rl-bpw5 install, users can directly use deepseek-math-7b-rl-bpw5 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

deepseek-math-7b-rl-bpw5 install url in huggingface.co:

https://huggingface.co/blockblockblock/deepseek-math-7b-rl-bpw5

Url of deepseek-math-7b-rl-bpw5

deepseek-math-7b-rl-bpw5 huggingface.co Url

Provider of deepseek-math-7b-rl-bpw5 huggingface.co

blockblockblock
ORGANIZATIONS

Other API from blockblockblock