2,750 Downloads Updated 1 year ago
Updated 1 year ago
1 year ago
0d70bffb5107 · 7.3GB ·
It’s https://huggingface.co/tastypear/deepseek-ai-deepseek-math-7b-rl-GGUF but on Ollama with a good system prompt.
Tags:
ollama run t1c/deepseek-math-7b-rl:latest
Q4_K_M (default)
ollama run t1c/deepseek-math-7b-rl:Q5
Q5_K_M
ollama run t1c/deepseek-math-7b-rl:Q6
Q6_K
ollama run t1c/deepseek-math-7b-rl:Q8
Q8_0
Here’s a shortened version of the readme from the original GitHub repo:
DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens. DeepSeekMath 7B has achieved an impressive score of 51.7% on the competition-level MATH benchmark without relying on external toolkits and voting techniques, approaching the performance level of Gemini-Ultra and GPT-4. For research purposes, we release checkpoints of base, instruct, and RL models to the public.
We conduct a comprehensive assessment of the mathematical capabilities of DeepSeekMath-Base 7B, focusing on its ability to produce self-contained mathematical solutions without relying on external tools, solve math problems using tools, and conduct formal theorem proving. Beyond mathematics, we also provide a more general profile of the base model, including its performance of natural language understanding, reasoning, and programming skills.
The evaluation results from the tables above can be summarized as follows: - Superior Mathematical Reasoning: On the competition-level MATH dataset, DeepSeekMath-Base 7B outperforms existing open-source base models by more than 10% in absolute terms through few-shot chain-of-thought prompting, and also surpasses Minerva 540B. - Strong Tool Use Ability: Continuing pre-training with DeepSeekCoder-Base-7B-v1.5 enables DeepSeekMath-Base 7B to more effectively solve and prove mathematical problems by writing programs. - Comparable Reasoning and Coding Performance: DeepSeekMath-Base 7B achieves performance in reasoning and coding that is comparable to that of DeepSeekCoder-Base-7B-v1.5.
DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B, while DeepSeekMath-RL 7B is trained on the foundation of DeepSeekMath-Instruct 7B, utilizing our proposed Group Relative Policy Optimization (GRPO) algorithm.
We evaluate mathematical performance both without and with tool use, on 4 quantitative reasoning benchmarks in English and Chinese. As shown in Table, DeepSeekMath-Instruct 7B demonstrates strong performance of step-by-step reasoning, and DeepSeekMath-RL 7B approaches an accuracy of 60% on MATH with tool use, surpassing all existing open-source models.
After four iterations of data collection, we end up with 35.5M mathematical web pages, totaling 120B tokens.
@misc{deepseek-math,
author = {Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y.K. Li, Y. Wu, Daya Guo},
title = {DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models},
journal = {CoRR},
volume = {abs/2402.03300},
year = {2024},
url = {https://arxiv.org/abs/2402.03300},
}
If you have any questions, please raise an issue or contact DeepSeek at service@deepseek.com.