dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-27 22:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

Cleaning up examples/ models and starter .env files (#1124)

Browse source 
Closes https://github.com/go-skynet/LocalAI/issues/1066 and
https://github.com/go-skynet/LocalAI/issues/1065

Standardizes all `examples/`:
- Models in one place (other than `rwkv`, which was one-offy)
- Env files as `.env.example` with `cp`
    - Also standardizes comments and links docs
This commit is contained in:
James Braza 2023-10-02 09:14:10 -07:00 • committed by GitHub
parent c223364816
commit e34b5f0119
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
34 changed files with 48 additions and 99 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/autoGPT/.env → examples/autoGPT/.env.example
View file

@ -1,5 +1,9 @@
# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
OPENAI_API_KEY=sk---anystringhere
OPENAI_API_BASE=http://api:8080/v1
# Models to preload at start
# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings
PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "name": "gpt-3.5-turbo"}, { "url": "github:go-skynet/model-gallery/bert-embeddings.yaml", "name": "text-embedding-ada-002"}]
# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings,
# see other options in the model gallery at https://github.com/go-skynet/model-gallery
PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "name": "gpt-3.5-turbo"}, { "url": "github:go-skynet/model-gallery/bert-embeddings.yaml", "name": "text-embedding-ada-002"}]

6
examples/autoGPT/README.md
View file

@ -10,12 +10,16 @@ git clone https://github.com/go-skynet/LocalAI
cd LocalAI/examples/autoGPT
cp -rfv .env.example .env
# Edit the .env file to set a different model by editing `PRELOAD_MODELS`.
vim .env
docker-compose run --rm auto-gpt
```
Note: The example automatically downloads the `gpt4all` model as it is under a permissive license. The GPT4All model does not seem to be enough to run AutoGPT. WizardLM-7b-uncensored seems to perform better (with `f16: true`).
See the `.env` configuration file to set a different model with the [model-gallery](https://github.com/go-skynet/model-gallery) by editing `PRELOAD_MODELS`.
## Without docker