Warning: file_put_contents(aCache/aDaily/post/opendatascience/--): Failed to open stream: No space left on device in /var/www/tg-me/post.php on line 50
Data Science by ODS.ai 🦜 | Telegram Webview: opendatascience/2251 -
Telegram Group & Telegram Channel
🌟 DeepCoder-14B

New code reasoning LLM fine-tuned from DeepSeek-R1-Distill-Qwen-14B using distributed RL with GRPO+ and iterative context lengthening. Trained on ~24K coding problems (TACO-Verified, PrimeIntellect SYNTHETIC-1, LCB v5), it improves Pass@1 on LiveCodeBench v5 to 60.6%, +7.6% over base and on par with OpenAI o3-mini.

- GRPO+: removes KL/entropy loss for stability; adds offline difficulty filtering, DAPO-inspired loss masking, and reward clipping.
- Iterative context scaling: 16K→32K→64K generalization with improved long-context reasoning.

Eval: Strong results on LiveCodeBench, Codeforces, HumanEval+

Open weightsπŸ”₯

https://huggingface.co/agentica-org/DeepCoder-14B-Preview

@opendatascience
Please open Telegram to view this post
VIEW IN TELEGRAM



tg-me.com/opendatascience/2251
Create:
Last Update:

🌟 DeepCoder-14B

New code reasoning LLM fine-tuned from DeepSeek-R1-Distill-Qwen-14B using distributed RL with GRPO+ and iterative context lengthening. Trained on ~24K coding problems (TACO-Verified, PrimeIntellect SYNTHETIC-1, LCB v5), it improves Pass@1 on LiveCodeBench v5 to 60.6%, +7.6% over base and on par with OpenAI o3-mini.

- GRPO+: removes KL/entropy loss for stability; adds offline difficulty filtering, DAPO-inspired loss masking, and reward clipping.
- Iterative context scaling: 16K→32K→64K generalization with improved long-context reasoning.

Eval: Strong results on LiveCodeBench, Codeforces, HumanEval+

Open weightsπŸ”₯

https://huggingface.co/agentica-org/DeepCoder-14B-Preview

@opendatascience

BY Data Science by ODS.ai 🦜




Share with your friend now:
tg-me.com/opendatascience/2251

View MORE
Open in Telegram


Data Science by ODS ai 🦜 Telegram | DID YOU KNOW?

Date: |

How Does Bitcoin Mining Work?

Bitcoin mining is the process of adding new transactions to the Bitcoin blockchain. It’s a tough job. People who choose to mine Bitcoin use a process called proof of work, deploying computers in a race to solve mathematical puzzles that verify transactions.To entice miners to keep racing to solve the puzzles and support the overall system, the Bitcoin code rewards miners with new Bitcoins. β€œThis is how new coins are created” and new transactions are added to the blockchain, says Okoro.

How Does Telegram Make Money?

Telegram is a free app and runs on donations. According to a blog on the telegram: We believe in fast and secure messaging that is also 100% free. Pavel Durov, who shares our vision, supplied Telegram with a generous donation, so we have quite enough money for the time being. If Telegram runs out, we will introduce non-essential paid options to support the infrastructure and finance developer salaries. But making profits will never be an end-goal for Telegram.

Data Science by ODS ai 🦜 from pl


Telegram Data Science by ODS.ai 🦜
FROM USA