LLaMa3

Creator

Creator

Created

Created

2024 Aug 21 4:56

Editor

Editor

Edited

Edited

2024 Oct 25 19:10

Refs

Refs

llama3-from-scratch
naklecha • Updated 2024 Nov 28 10:53

LLaMa3 Varients

Audio

🍓 Ichigo: Llama learns to talk – Homebrew

With the latest checkpoint, we're teaching AI to talk and recognize when it can't listen.

🍓 Ichigo: Llama learns to talk – Homebrew

https://homebrew.ltd/blog/llama-learns-to-talk

🍓 Ichigo: Llama learns to talk – Homebrew

GPT4-V level LLaMa3 Vision

OpenBMB • Updated 2024 Nov 28 7:4

openbmb/MiniCPM-Llama3-V-2_5 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

openbmb/MiniCPM-Llama3-V-2_5 · Hugging Face

https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5

openbmb/MiniCPM-Llama3-V-2_5 · Hugging Face

MiniCPM-Llama3-V-2 5 - a Hugging Face Space by openbmb

Discover amazing ML apps made by the community

MiniCPM-Llama3-V-2 5 - a Hugging Face Space by openbmb

https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5

MiniCPM-Llama3-V-2 5 - a Hugging Face Space by openbmb

Official

Meta Llama 3 - a meta-llama Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases

Meta Llama 3 - a meta-llama Collection

https://huggingface.co/collections/meta-llama/meta-llama-3-66214712577ca38149ebb2b6

Meta Llama 3 - a meta-llama Collection

Build the future of AI with Meta Llama 3. Now available with both 8B and 70B pretrained and instruction-tuned versions to support a wide range of applications.

https://llama.meta.com/llama3/

8b-1048k

gradientai/Llama-3-8B-Instruct-Gradient-1048k · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

gradientai/Llama-3-8B-Instruct-Gradient-1048k · Hugging Face

https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k

gradientai/Llama-3-8B-Instruct-Gradient-1048k · Hugging Face

NousResearch/Hermes-2-Pro-Llama-3-8B · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

NousResearch/Hermes-2-Pro-Llama-3-8B · Hugging Face

https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B

NousResearch/Hermes-2-Pro-Llama-3-8B · Hugging Face

nvidia/Llama3-ChatQA-1.5-70B · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

nvidia/Llama3-ChatQA-1.5-70B · Hugging Face

https://huggingface.co/nvidia/Llama3-ChatQA-1.5-70B

nvidia/Llama3-ChatQA-1.5-70B · Hugging Face

mlabonne/Meta-Llama-3-120B-Instruct · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

mlabonne/Meta-Llama-3-120B-Instruct · Hugging Face

https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct

mlabonne/Meta-Llama-3-120B-Instruct · Hugging Face

Model Quantization

Introducing quantized Llama models with increased speed and a reduced memory footprint

As our first quantized models in this Llama category, these instruction-tuned models retain the quality and safety of the original 1B and 3B models, while achieving 2-4x speedup.

Introducing quantized Llama models with increased speed and a reduced memory footprint

https://ai.meta.com/blog/meta-llama-quantized-lightweight-models/

Introducing quantized Llama models with increased speed and a reduced memory footprint

Recommendations

/////////