Mistral Large 2 (2407) is now on @lmsysorg
. It performs extremely well in the Coding, Hard Prompts, Math, and Longer Query categories, where it outperforms GPT4-Turbo and Claude 3 Opus. It is also doing very well in Instruction Following where it ranks above Llama 3.1 405B.
OPEN SOURCE
-
Mistral Large 2 Excels in Coding, Math, and Hard Prompts
By
–
-
Open-source AI models: transparency over performance gains
By
–
Open-source AI models are like sport without doping Performances can be slightly lower but in the end, transparency is more sustainable, healthy and exciting to watch and participate in 🙂
-
Experimenting with Model Merging and Quantization Techniques
By
–
Anyway, have fun quantizing and running this monster! This is a silly experiment but who knows, we might: 1/ Realize it's good at something, like creative writing
2/ Get some insights into how to create these self-merges Good luck everyone and make your own frankenmerges -
BigLlama-3.1-681B-Instruct: New Intermediate Checkpoint Released
By
–
Because 1T parameters might be a bit too much, I'm also releasing an "intermediate checkpoint": BigLlama-3.1-681B-Instruct. It's closer to what Llama 3 120B was to the 70B, so it might be more coherent as well. Model: https://
huggingface.co/mlabonne/BigLl
ama-3.1-681B-Instruct
… -
BigLlama-3.1 reaches 1 trillion parameters milestone
By
–
BigLlama-3.1-1T-Instruct So I've heard that 405B parameters weren't enough… It's my pleasure to present an upscaled Llama 3.1 with 1,000,000,000 parameters. Now available on @huggingface
. Model: https://
huggingface.co/mlabonne/BigLl
ama-3.1-1T-Instruct
… -
MiniCPM-V: GPT-4V Level MLLM for Mobile Devices
By
–
MiniCPM-V A GPT-4V Level MLLM on Your Phone paper page: https://
huggingface.co/papers/2408.01
800
… The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone. -
MeshAnything V2: Artist-Created Mesh Generation with Adjacent Tokenization
By
–
MeshAnything V2
— AK (@_akhaliq) 6 août 2024
Artist-Created Mesh Generation with Adjacent Mesh Tokenization
demo: https://t.co/QXRUqBcyrI
Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything… pic.twitter.com/hEnAlVhF8rMeshAnything V2 Artist-Created Mesh Generation with Adjacent Mesh Tokenization demo: https://
huggingface.co/spaces/Yiwen-n
tu/MeshAnythingV2
… Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything -
Fastcore: An Underrated Python Library Worth Exploring
By
–
tbh someone needs to write "'fastcore: An Underrated Python Library': An Underrated Blog Post".
-
NeuralGCM Open Source AI Tool for Climate Modeling
By
–
Announcing that NeuralGCM is now openly available on @github
. Join us in building the future #AI tool for climate modeling https://
goo.gle/3Wr3o9e -
Software Archaeologists Find Years-Old Solution to Problem
By
–
Software archeologists discovered that a solution to the entire problem had been freely available for years.