Telegram Group & Telegram Channel
DeepScaleR-1.5B-Preview

DeepscaleR-1.5b 是在 DeepSeekR1-distilled-Qwen1.5b 上仅使用 3800 A100h(~$4500) 进行 RL 微调的 LLM

该模型在 AIME 2024 上获得了 43.1%@1 的准确性,较基底(28.8%)提高 14%,在 1.5B 参数下超过了 o1-preview
(Arena Math 中 R1>Gemini 2 Thinking>o1p>Gemini 2 Pro)

Open sourced dataset, code, training logs and models
Github: Github.com/agentica-project/deepscaler
Inference GGUF
#AI



group-telegram.com/GaryNoHeya/2918
Create:
Last Update:

DeepScaleR-1.5B-Preview

DeepscaleR-1.5b 是在 DeepSeekR1-distilled-Qwen1.5b 上仅使用 3800 A100h(~$4500) 进行 RL 微调的 LLM

该模型在 AIME 2024 上获得了 43.1%@1 的准确性,较基底(28.8%)提高 14%,在 1.5B 参数下超过了 o1-preview
(Arena Math 中 R1>Gemini 2 Thinking>o1p>Gemini 2 Pro)

Open sourced dataset, code, training logs and models
Github: Github.com/agentica-project/deepscaler
Inference GGUF
#AI

BY Garyの梦呓






Share with your friend now:
group-telegram.com/GaryNoHeya/2918

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Soloviev also promoted the channel in a post he shared on his own Telegram, which has 580,000 followers. The post recommended his viewers subscribe to "War on Fakes" in a time of fake news. Telegram boasts 500 million users, who share information individually and in groups in relative security. But Telegram's use as a one-way broadcast channel — which followers can join but not reply to — means content from inauthentic accounts can easily reach large, captive and eager audiences. Telegram users are able to send files of any type up to 2GB each and access them from any device, with no limit on cloud storage, which has made downloading files more popular on the platform. Russian President Vladimir Putin launched Russia's invasion of Ukraine in the early-morning hours of February 24, targeting several key cities with military strikes. But because group chats and the channel features are not end-to-end encrypted, Galperin said user privacy is potentially under threat.
from sa


Telegram Garyの梦呓
FROM American