Skip to content

Mistral AI and GGUF and Qwen support #1125

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 26, 2023
Merged

Mistral AI and GGUF and Qwen support #1125

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1966be8
Mistral AI, say hi to PostresML
levkk Oct 26, 2023
e948002
Deps
levkk Oct 26, 2023
cfc8365
tokenizers
levkk Oct 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/ubuntu-packages-and-docker-image.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ on:
workflow_dispatch:
inputs:
packageVersion:
default: "2.7.12"
default: "2.7.13"
jobs:
#
# PostgresML extension.
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/ubuntu-postgresml-python-package.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ on:
workflow_dispatch:
inputs:
packageVersion:
default: "2.7.12"
default: "2.7.13"

jobs:
postgresml-python:
Expand Down
2 changes: 1 addition & 1 deletion packages/postgresml/DEBIAN/control
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ Version: ${PACKAGE_VERSION}
Section: database
Priority: optional
Architecture: all
Depends: postgresml-python (>= 2.7.12), postgresql-pgml-${PGVERSION} (>= ${PACKAGE_VERSION})
Depends: postgresml-python (>= 2.7.13), postgresql-pgml-${PGVERSION} (>= ${PACKAGE_VERSION})
Maintainer: PostgresML <team@postgresml.org>
Homepage: https://postgresml.org
Description: PostgresML - Generative AI and Simple ML inside PostgreSQL
Expand Down
2 changes: 1 addition & 1 deletion pgml-extension/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion pgml-extension/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[package]
name = "pgml"
version = "2.7.12"
version = "2.7.13"
edition = "2021"

[lib]
Expand Down
6 changes: 4 additions & 2 deletions pgml-extension/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,13 +16,15 @@ sacremoses==0.0.53
scikit-learn==1.3.0
sentencepiece==0.1.99
sentence-transformers==2.2.2
tokenizers==0.13.3
tokenizers==0.14.1
torch==2.0.1
torchaudio==2.0.2
torchvision==0.15.2
tqdm==4.66.1
transformers==4.33.1
transformers==4.34.1
xgboost==2.0.0
langchain==0.0.287
einops==0.6.1
pynvml==11.5.0
transformers-stream-generator==0.0.4
optimum==1.13.2
Empty file added pgml-extension/sql/pgml--2.7.12--2.7.13.sql
View file
Open in desktop
Empty file.
2 changes: 1 addition & 1 deletion pgml-extension/src/bindings/transformers/transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,7 +197,7 @@ def create_pipeline(task):
lower = model_name.lower()
else:
lower = None
if lower and "-ggml" in lower:
if lower and ("-ggml" in lower or "-gguf" in lower):
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kczimm these run on the CPU, so could be useful for local dev on a M1. I'll try on my end just to be sure (on my desktop right now)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Worked on my M1 after uninstalling deepspeed.

pipe = GGMLPipeline(model_name, **task)
elif lower and "-gptq" in lower:
pipe = GPTQPipeline(model_name, **task)
Expand Down