AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update gpt4all_python_embedding.md

Browse Source 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
This commit is contained in:
Andriy Mulyar 2023-07-14 14:30:14 -04:00 committed by GitHub
parent f543affa9a
commit 89e277bb3c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gpt4all-bindings/python/docs/gpt4all_python_embedding.md
View File

@ -1,5 +1,5 @@
# GPT4All Python Embedding API
GPT4All includes a super simple means of generating embeddings for your text documents.
# Embeddings
GPT4All supports generating high quality embeddings of arbitrary length documents of text using a CPU optimized contrastively trained [Sentence Transformer](https://www.sbert.net/). These embeddings are comparable in quality for many tasks with OpenAI.
## Quickstart
@ -25,7 +25,7 @@ The embedding model will automatically be downloaded if not installed.
### Speed of embedding generation
The following table lists the generation speed for text documents of N tokens captured on an Intel i913900HX CPU with DDR5 5600 running with 8 threads under stable load.
| Tokens | 2^7 | 2^9 | 2^11 | 2^13 | 2^14 |
| Tokens | 128 | 512 | 2048 | 8129 | 2^14 |
| --------------- | ---- | ---- | ---- | ---- | ---- |
| Wall time (s) | .02 | .08 | .24 | .96 | 1.9 |
| Tokens / Second | 6508 | 6431 | 8622 | 8509 | 8369 |