Our great sponsors
-
InfluxDB
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.
-
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
xpk
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.
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:
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
They have implemented the model also on their own C++ inference engine: https://github.com/google/gemma.cpp
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).
It should be possible to run it via llama.cpp[0] now.
[0] https://github.com/ggerganov/llama.cpp/pull/5631
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.
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.
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.
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.