From 1d9401ddceca53fd2a3d21e48c656242c65c6692 Mon Sep 17 00:00:00 2001 From: Alexander Borzunov Date: Fri, 22 Sep 2023 06:16:32 +0400 Subject: [PATCH] Update README.md (#520) --- README.md | 109 ++++++------------------------------------------------ 1 file changed, 12 insertions(+), 97 deletions(-) diff --git a/README.md b/README.md index 1f410ef..63449ae 100644 --- a/README.md +++ b/README.md @@ -8,14 +8,14 @@

-Generate text with distributed **Llama 2 (70B)**, **Stable Beluga 2**, **Falcon**, **Guanaco-65B** or **BLOOM-176B** and fine‑tune them for your own tasks — right from your desktop computer or Google Colab: +Generate text with distributed **Llama 2** (70B), **Falcon** (40B+), **BLOOM** (176B) (or their derivatives), and fine‑tune them for your own tasks — right from your desktop computer or Google Colab: ```python from transformers import AutoTokenizer from petals import AutoDistributedModelForCausalLM # Choose any model available at https://health.petals.dev -model_name = "petals-team/StableBeluga2" +model_name = "petals-team/StableBeluga2" # This one is fine-tuned Llama 2 (70B) # Connect to a distributed network hosting model layers tokenizer = AutoTokenizer.from_pretrained(model_name) @@ -31,9 +31,9 @@ print(tokenizer.decode(outputs[0])) # A cat sat on a mat... 🚀  Try now in Colab

-🦙 **Want to run Llama 2?** Request access to its weights at the ♾️ [Meta AI website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and 🤗 [Model Hub](https://huggingface.co/meta-llama/Llama-2-70b-hf), then run `huggingface-cli login` in the terminal before loading the model. Or just try it in our [chatbot app](https://chat.petals.dev). +🔏 **Privacy.** Your data will be processed with the help of other people in the public swarm. Learn more about privacy [here](https://github.com/bigscience-workshop/petals/wiki/Security,-privacy,-and-AI-safety). For sensitive data, you can set up a [private swarm](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) among people you trust. -🔏 **Privacy.** Your data will be processed by other people in the public swarm. Learn more about privacy [here](https://github.com/bigscience-workshop/petals/wiki/Security,-privacy,-and-AI-safety). For sensitive data, you can set up a [private swarm](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) among people you trust. +🦙 **Want to run Llama 2?** Request access to its weights at the ♾️ [Meta AI website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and 🤗 [Model Hub](https://huggingface.co/meta-llama/Llama-2-70b-hf), then run `huggingface-cli login` in the terminal before loading the model. Or just try it in our [chatbot app](https://chat.petals.dev). 💬 **Any questions?** Ping us in [our Discord](https://discord.gg/KdThf2bWVU)! @@ -81,9 +81,8 @@ python3 -m petals.cli.run_server petals-team/StableBeluga2 ## How does it work? -- Petals runs large language models like [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) and [BLOOM](https://huggingface.co/bigscience/bloom) **collaboratively** — you load a small part of the model, then join people serving the other parts to run inference or fine-tuning. -- Single-batch inference runs at **up to 6 steps/sec** for **Llama 2** (70B) and ≈ 1 step/sec for BLOOM-176B. This is [up to 10x faster](https://github.com/bigscience-workshop/petals#benchmarks) than offloading, enough to build [chatbots](https://chat.petals.dev) and other interactive apps. Parallel inference reaches hundreds of tokens/sec. -- Beyond classic language model APIs — you can employ any fine-tuning and sampling methods, execute custom paths through the model, or see its hidden states. You get the comforts of an API with the flexibility of PyTorch. +- You load a small part of the model, then join a [network](https://health.petals.dev) of people serving the other parts. Single‑batch inference runs at up to **6 tokens/sec** for **Llama 2** (70B) and up to **4 tokens/sec** for **Falcon** (180B) — enough for [chatbots](https://chat.petals.dev) and interactive apps. +- You can employ any fine-tuning and sampling methods, execute custom paths through the model, or see its hidden states. You get the comforts of an API with the flexibility of **PyTorch** and **🤗 Transformers**.

@@ -113,99 +112,15 @@ Advanced guides: - Launch a private swarm: [guide](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) - Run a custom model: [guide](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-Petals) -## Benchmarks - -The benchmarks below are for BLOOM-176B: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
NetworkSingle-batch inference
(steps/s)		Parallel forward
(tokens/s)
BandwidthRound-trip
latency		Sequence lengthBatch size
1282048164
Offloading, max. possible speed on 1x A100 1
256 Gbit/s0.180.182.7170.3
128 Gbit/s0.090.092.4152.8
Petals on 14 heterogeneous servers across Europe and North America 2
Real world0.830.7932.6179.4
Petals on 3 servers, with one A100 each 3
1 Gbit/s< 5 ms1.711.5470.0253.6
100 Mbit/s< 5 ms1.661.4956.4182.0
100 Mbit/s100 ms1.231.1119.7112.2
- -1 **An upper bound for offloading performance.** We base our offloading numbers on the best possible hardware setup for offloading: CPU RAM offloading via PCIe 4.0 with 16 PCIe lanes per GPU and PCIe switches for pairs of GPUs. We assume zero latency for the upper bound estimation. In 8-bit, the model uses 1 GB of memory per billion parameters. PCIe 4.0 with 16 lanes has a throughput of 256 Gbit/s, so offloading 176B parameters takes 5.5 seconds. The throughput is twice as slow (128 Gbit/s) if we have two GPUs behind the same PCIe switch. - -2 **A real-world distributed setting** with 14 servers holding 2× RTX 3060, 4× 2080Ti, 2× 3090, 2× A4000, and 4× A5000 GPUs. These are personal servers and servers from university labs, spread across Europe and North America and connected to the Internet at speeds of 100–1000 Mbit/s. 4 servers operate from under firewalls. - -3 **An optimistic setup** that requires least communication. The client nodes have 8 CPU cores and no GPU. - -We provide more evaluations and discuss these results in more detail in **Section 3.3** of our [paper](https://arxiv.org/pdf/2209.01188.pdf). - -## 🛠️ Contributing +### Benchmarks + +Please see **Section 3.3** of our [paper](https://arxiv.org/pdf/2209.01188.pdf). + +### 🛠️ Contributing Please see our [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions#contributing) on contributing. -## 📜 Citation +### 📜 Citation Alexander Borzunov, Dmitry Baranchuk, Tim Dettmers, Max Ryabinin, Younes Belkada, Artem Chumachenko, Pavel Samygin, and Colin Raffel. [Petals: Collaborative Inference and Fine-tuning of Large Models.](https://arxiv.org/abs/2209.01188)