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: |

That strategy is the acquisition of a value-priced company by a growth company. Using the growth company's higher-priced stock for the acquisition can produce outsized revenue and earnings growth. Even better is the use of cash, particularly in a growth period when financial aggressiveness is accepted and even positively viewed.he key public rationale behind this strategy is synergy - the 1+1=3 view. In many cases, synergy does occur and is valuable. However, in other cases, particularly as the strategy gains popularity, it doesn't. Joining two different organizations, workforces and cultures is a challenge. Simply putting two separate organizations together necessarily creates disruptions and conflicts that can undermine both operations.

The SSE was the first modern stock exchange to open in China, with trading commencing in 1990. It has now grown to become the largest stock exchange in Asia and the third-largest in the world by market capitalization, which stood at RMB 50.6 trillion (US$7.8 trillion) as of September 2021. Stocks (both A-shares and B-shares), bonds, funds, and derivatives are traded on the exchange. The SEE has two trading boards, the Main Board and the Science and Technology Innovation Board, the latter more commonly known as the STAR Market. The Main Board mainly hosts large, well-established Chinese companies and lists both A-shares and B-shares.

Data Science by ODS ai 🦜 from in


Telegram Data Science by ODS.ai 🦜
FROM USA