DeepSeek-Coder-V2: First Open Source Model Beats GPT4-Turbo in Coding and Math
> Excels in coding and math, beating GPT4-Turbo, Claude3-Opus, Gemini-1.5Pro, Codestral.
> Supports 338 programming languages and 128K context length.
> Fully open-sourced with two sizes: 230B (also with API access) and 16B.
#DeepSeekCoder
SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench!
Check out SWE-agent in action at https://t.co/1NNL526gMy
Repo: https://t.co/LsgeVvD1UC
What a week, huh?
Captain, it's only Thursday
- @databricks releases DBRX, a 132B MoE
- @AI21Labs releases Jamba, a 52B Transformer/Mamba MoE
- @AlibabaGroup releases Qwen-1.5-MoE, a 2.7B MoE
All on https://t.co/PHNLufiqcQ! 🤗
Learn about MoE here: https://t.co/fYxmn77sys
There's a new king of open-source.
The new LLM from @databricks just beat Mixtral!
- 132B total params (16 experts), 36B active (4 experts)
- Trained on *12T* tokens
- 32K context length
From my initial tests, I'm really impressed.
Today we're excited to introduce Devin, the first AI software engineer.
Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork.
Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser.
When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted.
Check out what Devin can do in the thread below.
With Google's new software, you’re less likely to get frustrating responses to queries dependent on prepositions like for” and “to,” or negations such as “not” or “no.” https://t.co/HDAv0pNlxG
Published a more detailed article about my solution agent that won the Microsoft TextWorld machine learning competition. The source code is also published in GitHub. #TextWorld https://t.co/6bkZO2ojK8
This Microsoft AI competition was extremely fun. The goal was to build an agent to solve text based games. Of course, I am super happy with the result 😀. The Microsoft blog post explains the competition and the solution I used to win it.
A team from #Cognitiva has won the #TextWorld competition, a Microsoft Research AI competition on reinforcement learning and natural language processing for solving text based games. Congratulations @pvl
The First TextWorld Problems competition enables researchers to have some fun with text-based games while making important strides in reinforcement learning and natural language processing. Find out who won and how their agent tackled the challenge: https://t.co/YlVCSELkWX