❗❗❗
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.
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.
deepseek-math-7b-rl-bpw2.25 huggingface.co is an AI model on huggingface.co that provides deepseek-math-7b-rl-bpw2.25's model effect (), which can be used instantly with this blockblockblock deepseek-math-7b-rl-bpw2.25 model. huggingface.co supports a free trial of the deepseek-math-7b-rl-bpw2.25 model, and also provides paid use of the deepseek-math-7b-rl-bpw2.25. Support call deepseek-math-7b-rl-bpw2.25 model through api, including Node.js, Python, http.
deepseek-math-7b-rl-bpw2.25 huggingface.co is an online trial and call api platform, which integrates deepseek-math-7b-rl-bpw2.25's modeling effects, including api services, and provides a free online trial of deepseek-math-7b-rl-bpw2.25, you can try deepseek-math-7b-rl-bpw2.25 online for free by clicking the link below.
blockblockblock deepseek-math-7b-rl-bpw2.25 online free url in huggingface.co:
deepseek-math-7b-rl-bpw2.25 is an open source model from GitHub that offers a free installation service, and any user can find deepseek-math-7b-rl-bpw2.25 on GitHub to install. At the same time, huggingface.co provides the effect of deepseek-math-7b-rl-bpw2.25 install, users can directly use deepseek-math-7b-rl-bpw2.25 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
deepseek-math-7b-rl-bpw2.25 install url in huggingface.co: