Yep i've seen this but I feel like it'd be cleaner to do a distinct file format for this (GGUF is very LLM centric, including metadata etc)
LLMS
-
AI Scientist Community Explores New Frontier Models
By
–
We love watching the community build with The AI Scientist since its release! We have a new community section in our repo and support more recent frontier models: https://
github.com/SakanaAI/AI-Sc
ientist
… Time to highlight awesome topics that people have explored with our system! Thread -
Cohere releases Aya 8B & 32B multilingual models for 23 languages
By
–
Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages ! @cohere just dropped two great models: great on generalist use, they specifically shine on 23 non-english languages. How did they pull that multilingual trick? 𝗧𝗿𝗮𝗶𝗻 𝗼𝗻 𝘀𝘆𝗻𝘁𝗵𝗲𝘁𝗶𝗰
-
Cohere Releases State-of-Art Multilingual AI Models
By
–
Our research lab, @CohereForAI released a new family of state-of-art multilingual AI models – the culmination of over two years of collaboration with researchers around the world and a series of technical breakthroughs to help close the language gap in AI! https://t.co/z0c2c29NuS
— Cohere (@cohere) 24 octobre 2024Our research lab, @CohereForAI released a new family of state-of-art multilingual AI models – the culmination of over two years of collaboration with researchers around the world and a series of technical breakthroughs to help close the language gap in AI!
-
Anthropic Improves Claude 3.5 Sonnet and Launches Haiku
By
–
[#Article] Anthropic announces an improved version of Claude 3.5 Sonnet, a new "Computer Use" feature and the new Claude 3.5 Haiku model https://actuia.com/actualite/anthropic-annonce-une-version-amelioree-de-claude-3-5-sonnet-une-nouvelle-fonctionnalite-computer-use-et-le-nouveau-modele-claude-3-5-haiku/
…
#AI #artificialintelligence -
Outlines Algorithms Ported to Rust for Faster Structured Generation
By
–
I've said it before: Structured generation is the future The @dottxtai team has ported its core Outlines algos to rust, which means from now on, structured LLM generation is: – faster
– more robust
– embeddable into any ML software (no need for Python anymore) ^#3 is my -
Install and Configure AutoTrain Advanced for Llama3 8B ORPO Fine-tuning
By
–
$ pip install autotrain-advanced
$ autotrain –config https://
raw.githubusercontent.com/huggingface/au
totrain-advanced/refs/heads/main/configs/llm_finetuning/llama3-8b-orpo.yml
… -
Make Sehun’s Dream Come True: New AI Research Breakthrough
By
–
Make Sehun's dream come true: https://
alphaxiv.org/abs/2410.14193 -
Claude 3.5 Sonnet Shows Robustness in Complex Tasks
By
–
One huge change I'm seeing in the new Claude 3.5 Sonnet model…it's more robust. I'm chucking complex decisions and code at it, and for each prompt, it's not only giving me "standard" output, it's giving flags, considerations, next steps, and alt decisions unprompted. LOVE.