Comments (4)
WebGPU currently only supports 16 and 32bit mode.
from transformers.js.
5.31 Gb for Renderer process
Can you confirm you do not have any other tabs open? I can't seem to understand how this can be related to the application (not much is being rendered).
4.16 Gb for GPU process
This makes sense since it's (most likely) running in fp16 mode.
from transformers.js.
@xenova can confirm:
- no opened tabs
- no browser extensions
Navigated to https://huggingface.co/spaces/Xenova/experimental-phi3-webgpu and loaded the model:
This makes sense since it's (most likely) running in fp16 mode.
Can we make it run in lower precision if we run q_4 quantization? (We can't, ONNX doesn't support 4q yet)
To avoid any confusion this is the downloaded model:
/Xenova/Phi-3-mini-4k-instruct_fp16/resolve/main/onnx/model_q4.onnx 838 mb
/Xenova/Phi-3-mini-4k-instruct_fp16/resolve/main/onnx/model_q4.onnx_data 1454mb
from transformers.js.
same here
from transformers.js.
Related Issues (20)
- Using AutoModel, AutoTokenizer with distilbert models HOT 1
- Support stopping criteria for sequence generation HOT 1
- WebGPU and WASM Backends Unavailable within Service Worker (V3 issue) HOT 2
- Is it possible to use transformers.js to implement audio source separation tasks? HOT 2
- Can I use Xenova/Phi-3-mini-4k-instruct model server side? HOT 2
- Implement BitNET
- env.allowLocalModels and env.allowRemoteModels HOT 1
- Feature request: YOLO-World/Grounding DINO (Zero shot object detection) HOT 2
- jinaai/jina-clip-v1: support for model names with prefixes HOT 1
- Support decision transformers HOT 2
- No performance gain on using WebGPU HOT 7
- Awesome project HOT 1
- Add the equivalent of output_hidden_layers HOT 4
- Implement documented generation config
- segment-anything-web Demo not working on iPhone
- Long running transcription using webgpu-whisper
- Decoding Tokens added by the user for Whisper models HOT 2
- Inaccurate Word Timestamps in ASR Transcription HOT 4
- RangeError: offset is out of bounds HOT 1
- Coin Master Free Spins - How To Get +99999 Free Spins In Coin Master (iOS & Android)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformers.js.