Telegram Group & Telegram Channel
Qwen QwQ实际用起来效果比几个DS蒸馏模型要强得多,试了之前几个经典问题都比DS用更少的token做出来。

可惜因为vocab有一些细微差异导致没法用qwen 2.5小模型来做draft model,以及因为众所周知的原因大概率热度远不如DS😆



tg-me.com/david_random/528
Create:
Last Update:

Qwen QwQ实际用起来效果比几个DS蒸馏模型要强得多,试了之前几个经典问题都比DS用更少的token做出来。

可惜因为vocab有一些细微差异导致没法用qwen 2.5小模型来做draft model,以及因为众所周知的原因大概率热度远不如DS😆

BY David's random thoughts


Warning: Undefined variable $i in /var/www/tg-me/post.php on line 283

Share with your friend now:
tg-me.com/david_random/528

View MORE
Open in Telegram


telegram Telegram | DID YOU KNOW?

Date: |

Telegram announces Search Filters

With the help of the Search Filters option, users can now filter search results by type. They can do that by using the new tabs: Media, Links, Files and others. Searches can be done based on the particular time period like by typing in the date or even “Yesterday”. If users type in the name of a person, group, channel or bot, an extra filter will be applied to the searches.

Telegram has exploded as a hub for cybercriminals looking to buy, sell and share stolen data and hacking tools, new research shows, as the messaging app emerges as an alternative to the dark web.An investigation by cyber intelligence group Cyberint, together with the Financial Times, found a ballooning network of hackers sharing data leaks on the popular messaging platform, sometimes in channels with tens of thousands of subscribers, lured by its ease of use and light-touch moderation.telegram from sg


Telegram David's random thoughts
FROM USA