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: |

Importantly, that investor viewpoint is not new. It cycles in when conditions are right (and vice versa). It also brings the ineffective warnings of an overpriced market with it.Looking toward a good 2022 stock market, there is no apparent reason to expect these issues to change.

That growth environment will include rising inflation and interest rates. Those upward shifts naturally accompany healthy growth periods as the demand for resources, products and services rise. Importantly, the Federal Reserve has laid out the rationale for not interfering with that natural growth transition.It's not exactly a fad, but there is a widespread willingness to pay up for a growth story. Classic fundamental analysis takes a back seat. Even negative earnings are ignored. In fact, positive earnings seem to be a limiting measure, producing the question, "Is that all you've got?" The preference is a vision of untold riches when the exciting story plays out as expected.

Data Science by ODS ai 🦜 from sg


Telegram Data Science by ODS.ai 🦜
FROM USA