alex/LocalAGI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: improve parameter generation by forcing reasoning (#193)

Browse Source 
* feat: improve parameter generation by forcing reasoning

Signed-off-by: mudler <mudler@localai.io>

* Update core/agent/actions.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update core/agent/actions.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Try to change default models

Signed-off-by: mudler <mudler@localai.io>

---------

Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto
2025-06-01 10:11:04 +02:00
committed by GitHub
parent f0dac5ca22
commit 56b6f7240c
4 changed files with 68 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@@ -63,7 +63,7 @@ MODEL_NAME=gemma-3-12b-it docker compose up
# NVIDIA GPU setup with custom multimodal and image models
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=minicpm-v-2_6 \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=flux.1-dev-ggml \
docker compose -f docker-compose.nvidia.yaml up
```
@@ -126,8 +126,8 @@ LocalAGI supports multiple hardware configurations through Docker Compose profil
- Supports text, multimodal, and image generation models
- Run with: `docker compose -f docker-compose.nvidia.yaml up`
- Default models:
- Text: `gemma-3-12b-it-qat`
- Multimodal: `minicpm-v-2_6`
- Text: `gemma-3-4b-it-qat`
- Multimodal: `moondream2-20250414`
- Image: `sd-1.5-ggml`
- Environment variables:
- `MODEL_NAME`: Text model to use
@@ -142,8 +142,8 @@ LocalAGI supports multiple hardware configurations through Docker Compose profil
- Supports text, multimodal, and image generation models
- Run with: `docker compose -f docker-compose.intel.yaml up`
- Default models:
- Text: `gemma-3-12b-it-qat`
- Multimodal: `minicpm-v-2_6`
- Text: `gemma-3-4b-it-qat`
- Multimodal: `moondream2-20250414`
- Image: `sd-1.5-ggml`
- Environment variables:
- `MODEL_NAME`: Text model to use
@@ -161,20 +161,20 @@ MODEL_NAME=gemma-3-12b-it docker compose up
# NVIDIA GPU with custom models
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=minicpm-v-2_6 \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=flux.1-dev-ggml \
docker compose -f docker-compose.nvidia.yaml up
# Intel GPU with custom models
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=minicpm-v-2_6 \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=sd-1.5-ggml \
docker compose -f docker-compose.intel.yaml up
```
If no models are specified, it will use the defaults:
- Text model: `gemma-3-12b-it-qat`
- Multimodal model: `minicpm-v-2_6`
- Text model: `gemma-3-4b-it-qat`
- Multimodal model: `moondream2-20250414`
- Image model: `sd-1.5-ggml`
Good (relatively small) models that have been tested are: