LocalLLaMA

localllama@sh.itjust.works

PostsComments

ikt@aussie.zoneEnglish · 10 months ago

"Flash Answers" Cerebras brings instant inference to Mistral Le Chat

0

1

"Flash Answers" Cerebras brings instant inference to Mistral Le Chat

ikt@aussie.zoneEnglish · 10 months ago

0

ikt@aussie.zoneEnglish · 10 months ago

Hibiki by kyutai, a simultaneous speech-to-speech translation model, currently supporting FR to EN

0

1

Hibiki by kyutai, a simultaneous speech-to-speech translation model, currently supporting FR to EN

ikt@aussie.zoneEnglish · 10 months ago

0

ikt@aussie.zoneEnglish · 10 months ago

DeepSeek gives Europe's tech firms a chance to catch up in global AI race

www.reuters.com

0

1

DeepSeek gives Europe's tech firms a chance to catch up in global AI race

www.reuters.com

ikt@aussie.zoneEnglish · 10 months ago

0

llama@lemmy.dbzer0.comEnglish · 10 months ago

How to run LLaMA (and other LLMs) on Android.

0

1

How to run LLaMA (and other LLMs) on Android.

llama@lemmy.dbzer0.comEnglish · 10 months ago

0

artificialfish@programming.devEnglish · 11 months ago

Has anyone applied tree of thought prompting to r1 yet?

0

1

Has anyone applied tree of thought prompting to r1 yet?

artificialfish@programming.devEnglish · 11 months ago

0

ikt@aussie.zoneEnglish · 11 months ago

Mistral Small 3 (24B) released

0

1

Mistral Small 3 (24B) released

ikt@aussie.zoneEnglish · 11 months ago

0

ikt@aussie.zoneEnglish · 11 months ago

Did DeepSeek R1 just pop nvidias bubble?

www.youtube.com

0

1

Did DeepSeek R1 just pop nvidias bubble?

www.youtube.com

ikt@aussie.zoneEnglish · 11 months ago

0

SmokeyDope@lemmy.worldMEnglish · 11 months ago

Why llms are suprisingly good at math, and what it means to process language.

0

1

Why llms are suprisingly good at math, and what it means to process language.

SmokeyDope@lemmy.worldMEnglish · 11 months ago

0

SmokeyDope@lemmy.worldMEnglish · 11 months ago

Thoughts on new deepseek R1 distill models

0

1

Thoughts on new deepseek R1 distill models

SmokeyDope@lemmy.worldMEnglish · 11 months ago

0

brokenlcd@feddit.itEnglish · 11 months ago

unsure on how to quantize model

0

1

unsure on how to quantize model

brokenlcd@feddit.itEnglish · 11 months ago

0

🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕠𝕕𝕚𝕝𝕖@lemm.eeEnglish · 11 months ago

How much gpu do i need to run a 90b model

3

1

How much gpu do i need to run a 90b model

🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕠𝕕𝕚𝕝𝕖@lemm.eeEnglish · 11 months ago

3

SmokeyDope@lemmy.worldMEnglish · 11 months ago

Nvidia Digits AI Supercomputer just announced

0

1

Nvidia Digits AI Supercomputer just announced

SmokeyDope@lemmy.worldMEnglish · 11 months ago

0

Halo@lemmy.worldEnglish · 11 months ago

Go toolchain error - Does anyone know what's going on here?

0

1

Go toolchain error - Does anyone know what's going on here?

Halo@lemmy.worldEnglish · 11 months ago

0

BB84@mander.xyzEnglish · 1 year ago

New open-weight 🐋 DeepSeek V3. 685B MoE. Beats Claude 3.5 Sonnet on Aider coding benchmark

0

1

New open-weight 🐋 DeepSeek V3. 685B MoE. Beats Claude 3.5 Sonnet on Aider coding benchmark

BB84@mander.xyzEnglish · 1 year ago

0

hok@lemmy.dbzer0.comEnglish · 1 year ago

Can you fine-tune on localized steering of an LLM?

0

1

Can you fine-tune on localized steering of an LLM?

hok@lemmy.dbzer0.comEnglish · 1 year ago

0

mapumbaa@lemmy.zipEnglish · 1 year ago

Questions about HW for local LLM.

0

1

Questions about HW for local LLM.

mapumbaa@lemmy.zipEnglish · 1 year ago

0

HumanPerson@sh.itjust.worksEnglish · 1 year ago

Fixed it

sh.itjust.works

0

1

Fixed it

sh.itjust.works

HumanPerson@sh.itjust.worksEnglish · 1 year ago

0

hok@lemmy.dbzer0.comEnglish · 1 year ago

Llama 3.3 70b - End of open-weight pretrained models from Meta or just a better Llama 3.1 405b finetune?

0

1

Llama 3.3 70b - End of open-weight pretrained models from Meta or just a better Llama 3.1 405b finetune?

hok@lemmy.dbzer0.comEnglish · 1 year ago

0

projectmoon@lemm.eeEnglish · 1 year ago

OpenWebUI OpenStreetMap Tool 2.1.0

0

1

OpenWebUI OpenStreetMap Tool 2.1.0

projectmoon@lemm.eeEnglish · 1 year ago

0

lynx@sh.itjust.worksEnglish · 1 year ago

Qwen2.5-Coder-7B

0

1

Qwen2.5-Coder-7B

lynx@sh.itjust.worksEnglish · 1 year ago

0

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

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.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

8 users / day
8 users / week
8 users / month
8 users / 6 months
3 local subscribers
3.15K subscribers
58 Posts
3 Comments
Modlog

sh.itjust.works

A bilingual (EN/FR) general-purpose instance located in eastern Canada! Powered by 99% renewable energy! Everyone is welcome eh.

Useful Links

Lemmy Getting Started Guide
Official Lemmy Support
Search communities across all lemmy instance
sh.itjust.works meta discussion community: !main@sh.itjust.works
sh.itjust.works Matrix chat: https://matrix.to/#/#sh.itjust.works:matrix.org

Donations

Rules:

Be respectful. Everyone should feel welcome here.
No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
No Ads / Spamming.
No pornography.

Règles :

Soyez respectueux. Tout le monde doit se sentir le bienvenu ici.
Pas de bigoterie - y compris le racisme, le sexisme, le capacitisme, l’homophobie, la transphobie ou la xénophobie.
Pas de publicités / Pas de spam.
Pas de pornographie.

Fediseer

Other UI options (more to come)

Monitoring Services

lemmy-meter.info