DeepSeek dropped the V3.1 Weight (huggingface.co)

submitted 11 hours ago by pepperfree@sh.itjust.works to c/localllama@sh.itjust.works

15 comments fedilink hide all child comments

Not what we expected...

top 15 comments

sorted by: hot top controversial new old

[-] 0x01@lemmy.ml 6 points 6 hours ago

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.

Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved.

Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.

The tool calling improvements are very welcome

[-] pepperfree@sh.itjust.works 1 points 5 hours ago

I wonder if we can extend the context length. It already fine-tuned with YaRN so we can't get free extend with that method.

[-] deafboy@lemmy.world 14 points 10 hours ago

Honestly, did the word "drop" change meaning in the past few months, or am I just crazy?

[-] TheBat@lemmy.world 18 points 10 hours ago

I can't tell if dropped means released or removed?

[-] terminatortwo@piefed.social 10 points 10 hours ago* (last edited 10 hours ago)

Not really, it’s just more common!

Drop is a contronym, it means its own opposite, and its use as “disappear” or “appear” extends waaay back. Eg. Usage as in Drop a line or drop a letter go as far as the 1700s.

So just a different line in a long history of drops.

https://www.oed.com/dictionary/drop_v

[-] glimse@lemmy.world 2 points 6 hours ago

Would "dropping" a letter not be letting it go from your hand into the mail box?

[-] Smokeydope@lemmy.world 8 points 10 hours ago* (last edited 10 hours ago)

Its an ambiguous slang statement that can mean several different things at once. It requires extra work to ground in a well-defined meaning.

Much in the same way 'going to the bank' could mean a financial institution or a river, 'dropping' something can mean releasing a new thing, stopping support, or physically fumbling an object on the ground. OP could have done a better job disambiguating with either different words or more context.

[-] pepperfree@sh.itjust.works 1 points 5 hours ago

Ah. Sorry, good thing I attached the related link.

[-] Smokeydope@lemmy.world 1 points 1 hour ago

Its all good this is the internet nobody but wordy pedantic types pays much attention or energy into being precise on post and comments. I just wanted to point out how ambiguity works because im currently studying it mathematically so this was a relevant thing for me to talk about. Thank you for sharing the link and contributing to the community!

[-] vividspecter@aussie.zone 3 points 10 hours ago* (last edited 10 hours ago)

More like in the past 10 years or so, but yes. On a side note, "leaked" has also subtly changed meaning from the actual product (such as a game being released early through piracy etc) to just information about the product.

[-] bobo@lemmy.ml 2 points 9 hours ago

"leaked" has also subtly changed meaning from the actual product (such as a game being released early through piracy etc) to just information about the product.

Just no... Information getting out despite attempts to conceal it, is the secondary meaning of that verb since at least the 19th century.

[-] vividspecter@aussie.zone 1 points 9 hours ago

Thanks for the correction. The latter meaning did gain more prominence in recent years in my perception, but it's not surprising that it already existed in the past.

[-] hummingbird@lemmy.world 3 points 10 hours ago

It's not you

[-] FaceDeer@fedia.io 7 points 10 hours ago

What's not what we expected?

[-] pepperfree@sh.itjust.works 1 points 5 hours ago

Everybody been rumoring about R2. So releasing this thing kinda unexpected

this post was submitted on 21 Aug 2025

37 points (100.0% liked)

LocalLLaMA

3565 readers

81 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago

MODERATORS

SkySyrup@sh.itjust.works

pax@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works