mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-08 11:39:57 -06:00
Code Issues Packages Projects Releases Wiki Activity

chore(model gallery): add menlo_lucy (#5886)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-07-23 11:51:51 +02:00
committed by GitHub
parent 324fecbb75
commit ee7e77b6c1
1 changed files with 33 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
gallery/index.yaml
View File

@@ -1763,6 +1763,39 @@
- filename: Omega-Qwen3-Atom-8B.Q4_K_M.gguf
sha256: ec3d531b985a619a36d117c2fdd049fd360ecbca70b6d3d6cc7e6127c1e5b6a4
uri: huggingface://prithivMLmods/Omega-Qwen3-Atom-8B-GGUF/Omega-Qwen3-Atom-8B.Q4_K_M.gguf
- !!merge <<: *qwen3
name: "menlo_lucy"
icon: https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/PA6JCiYLPJX_WFO42ClTd.jpeg
urls:
- https://huggingface.co/Menlo/Lucy
- https://huggingface.co/bartowski/Menlo_Lucy-GGUF
description: |
Lucy is a compact but capable 1.7B model focused on agentic web search and lightweight browsing. Built on Qwen3-1.7B, Lucy inherits deep research capabilities from larger models while being optimized to run efficiently on mobile devices, even with CPU-only configurations.
We achieved this through machine-generated task vectors that optimize thinking processes, smooth reward functions across multiple categories, and pure reinforcement learning without any supervised fine-tuning.
overrides:
parameters:
model: Menlo_Lucy-Q4_K_M.gguf
files:
- filename: Menlo_Lucy-Q4_K_M.gguf
sha256: 1cb1682a9dbea9a1c8406721695f3faf6a212554d283585f2ec4608921f7c8b7
uri: huggingface://bartowski/Menlo_Lucy-GGUF/Menlo_Lucy-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "menlo_lucy-128k"
icon: https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/PA6JCiYLPJX_WFO42ClTd.jpeg
urls:
- https://huggingface.co/Menlo/Lucy-128k
- https://huggingface.co/bartowski/Menlo_Lucy-128k-GGUF
description: |
Lucy is a compact but capable 1.7B model focused on agentic web search and lightweight browsing. Built on Qwen3-1.7B, Lucy inherits deep research capabilities from larger models while being optimized to run efficiently on mobile devices, even with CPU-only configurations.
We achieved this through machine-generated task vectors that optimize thinking processes, smooth reward functions across multiple categories, and pure reinforcement learning without any supervised fine-tuning.
overrides:
parameters:
model: Menlo_Lucy-128k-Q4_K_M.gguf
files:
- filename: Menlo_Lucy-128k-Q4_K_M.gguf
sha256: fb3e591cccc5d2821f3c615fd6dc2ca86d409f56fbc124275510a9612a90e61f
uri: huggingface://bartowski/Menlo_Lucy-128k-GGUF/Menlo_Lucy-128k-Q4_K_M.gguf
- &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it"