Mixtral 8x22B Instruct is available on our platform, along with all our models: https://
console.mistral.ai The base and the instruct models are also both available for download on Hugging Face ! https://
huggingface.co/mistralai/Mixt
ral-8x22B-v0.1
… https://
huggingface.co/mistralai/Mixt
ral-8x22B-Instruct-v0.1
… 3/n
OPEN SOURCE
-
Mixtral 8x22B Instruct Model Released on Mistral Platform
By
–
-
Mixtral excels in science, code, and multilingual tasks
By
–
Mixtral particularly shines in science, code, and multilingual (below are performance results for the base model). 2/n
-
Mixtral 8x22B Instruct Released with Superior Performance
By
–
Mixtral 8x22B Instruct is out. It significantly outperforms existing open models, and only uses 39B active parameters (making it significantly faster than 70B models during inference). 1/n
-
Apache 2.0 Open Source AI Model Released Today
By
–
Official now, very proud of the team! Apache 2.0 and instructed versions for your pleasure, available today on la Plateforme
-
Microsoft invests in UAE AI as industry expands
By
–
Top stories in AI today: -Microsoft invests $1.5B in UAE AI firm
-AMD and Nvidia unveil new processors
-Access the best open-source LLM for free
-InstantMesh enables 3D generation in seconds
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/microsofts-u
ae-power-play
… -
MongoDB FireworksAI Llama Index AI Hackathon San Francisco
By
–
Join us this Saturday, April 20th at the @MongoDB with @FireworksAI_HQ @llama_index AI Hackathon in SF. Sigh up at https://
lnkd.in/gGcaDXaX and meet @upstageai #solarllm and full-stack LLM. -
Cross-language package.json parsing for dependency management tools
By
–
This is about more than just Node.js compatibility There are plenty of reasons people might want to read package.json from other tools – running a dependency audit using a tool written in Python or Go or jq for example
-
Free Workshop: Fine-tune LLMs with Ludwig and LoRAX
By
–
Ready to fine-tune and serve your own #LLM that outperforms #GPT4 — for free? Join our virtual #workshop to get hands on with open-source #Ludwig + #LoRAX and learn how to fine-tune and serve #LoRA adapters for customer support use cases! https://
pbase.ai/49DJvk2 -
Following Up on Stream Repos and Temporal Workflow Setup
By
–
following up on some repos from the stream (sorry for delay, merely got lazy) – @yikesawjeez https://
github.com/swyxio/devin-d
ocker-ui/
…
– @studentfoundersclub https://
github.com/swyxio/devin-c
loudflare-upload/
…
– building a @temporalio workflow by reading docs and setting up a local cluster (cant remb who asked for this) -
Local LLMs Weaker Than Hosted Models Like Claude 3
By
–
Most local LLMs are way, way weaker than hosted ones for most purposes – the best I've tried myself has been Mixtral 8x7B but it's still not in the same class as Claude 3 Haiku I haven't run 8x22B locally myself yet, I don't have the RAM for it