JingyaoLi commited on
Commit
26eb9bf
·
1 Parent(s): f1bd609

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -9,7 +9,8 @@ tags:
9
 
10
  # MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
11
 
12
- This is the official model repository of [MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks](https://arxiv.org/abs/2312.15960).
 
13
 
14
  ## Abstract
15
  Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that conventional models often generate solutions as monolithic code blocks, restricting their effectiveness in tackling intricate questions. To overcome this limitation, we present Modular-of-Thought Coder (MoTCoder). We introduce a pioneering framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules.
 
9
 
10
  # MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
11
 
12
+ This is the official model repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks.
13
+ [[Paper]](https://arxiv.org/abs/2312.15960), [[GitHub]](https://github.com/dvlab-research/MoTCoder).
14
 
15
  ## Abstract
16
  Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that conventional models often generate solutions as monolithic code blocks, restricting their effectiveness in tackling intricate questions. To overcome this limitation, we present Modular-of-Thought Coder (MoTCoder). We introduce a pioneering framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules.