Gemma: New Open Models

• gemma_pytorch

  6 5,077 7.7 Python

  The official PyTorch implementation of Google's Gemma models

  

https://github.com/google/gemma_pytorch/blob/main/tokenizer/...

I decoded this model protobuf in Python and here is the diff with the Llama 2 tokenizer:

• ollama

  220 69,806 9.9 Go

  Get up and running with Llama 3, Mistral, Gemma, and other large language models.

  

Already available in Ollama v0.1.26 preview release, if you'd like to start playing with it locally:

- https://github.com/ollama/ollama/releases/tag/v0.1.26

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• gemma.cpp

  8 5,600 9.3 C++

  lightweight, standalone C++ inference engine for Google's Gemma models.

  

They have implemented the model also on their own C++ inference engine: https://github.com/google/gemma.cpp

• gemma

  3 2,125 5.6 Jupyter Notebook

  Open weights LLM from Google DeepMind.

  

We've documented the architecture (including key differences) in our technical report here (https://goo.gle/GemmaReport), and you can see the architecture implementation in our Git Repo (https://github.com/google-deepmind/gemma).

• llama.cpp

  787 58,856 10.0 C++

  LLM inference in C/C++

It should be possible to run it via llama.cpp[0] now.

[0] https://github.com/ggerganov/llama.cpp/pull/5631

• text-to-text-transfer-transformer

  29 5,939 5.0 Python

  Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

  

Google released the T5 paper about 5 years ago:

https://arxiv.org/abs/1910.10683

This included full model weights along with a detailed description of the dataset, training process, and ablations that led them to that architecture. T5 was state-of-the-art on many benchmarks when it was released, but it was of course quickly eclipsed by GPT-3.

Following GPT-3, it became much more common for labs to not release full details or model weights. Prior to that, it was common practice from Google (BERT, T5), Meta (BART), OpenAI (GPT1, GPT2) and others to release full training details and model weights.

• ai-on-gke

  2 164 9.8 Jupyter Notebook
  

There is a lot of work to make the actual infrastructure and lower level management of lots and lots of GPUs/TPUs open as well - my team focuses on making the infrastructure bit at least a bit more approachable on GKE and Kubernetes.

https://github.com/GoogleCloudPlatform/ai-on-gke/tree/main

and

https://github.com/google/xpk (a bit more focused on HPC, but includes AI)

and

https://github.com/stas00/ml-engineering (not associated with GKE, but describes training with SLURM)

The actual training is still a bit of a small pool of very experienced people, but it's getting better. And every day serving models gets that much faster - you can often simply draft on Triton and TensorRT-LLM or vLLM and see significant wins month to month.

• SaaSHub

  www.saashub.com featured

  SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

  

• xpk

  1 59 9.0 Python

  xpk (Accelerated Processing Kit, pronounced x-p-k,) is a software tool to help Cloud developers to orchestrate training jobs on accelerators such as TPUs and GPUs on GKE.

  

There is a lot of work to make the actual infrastructure and lower level management of lots and lots of GPUs/TPUs open as well - my team focuses on making the infrastructure bit at least a bit more approachable on GKE and Kubernetes.

https://github.com/GoogleCloudPlatform/ai-on-gke/tree/main

and

https://github.com/google/xpk (a bit more focused on HPC, but includes AI)

and

https://github.com/stas00/ml-engineering (not associated with GKE, but describes training with SLURM)

The actual training is still a bit of a small pool of very experienced people, but it's getting better. And every day serving models gets that much faster - you can often simply draft on Triton and TensorRT-LLM or vLLM and see significant wins month to month.

• ml-engineering

  9 9,995 9.7 Python

  Machine Learning Engineering Open Book

There is a lot of work to make the actual infrastructure and lower level management of lots and lots of GPUs/TPUs open as well - my team focuses on making the infrastructure bit at least a bit more approachable on GKE and Kubernetes.

https://github.com/GoogleCloudPlatform/ai-on-gke/tree/main

and

https://github.com/google/xpk (a bit more focused on HPC, but includes AI)

and

https://github.com/stas00/ml-engineering (not associated with GKE, but describes training with SLURM)

The actual training is still a bit of a small pool of very experienced people, but it's getting better. And every day serving models gets that much faster - you can often simply draft on Triton and TensorRT-LLM or vLLM and see significant wins month to month.

Suggest a related project