chore(model gallery): add arcee-ai_homunculus (#5577)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-06-04 10:02:15 +02:00 committed by GitHub
parent 8b889955b4
commit 7a7d36ad63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -954,6 +954,21 @@
- filename: mrm8488_Qwen3-14B-ft-limo-Q4_K_M.gguf - filename: mrm8488_Qwen3-14B-ft-limo-Q4_K_M.gguf
sha256: 19d6dfd4a470cb293ad5e96bd94689fa2d12d1024eac548479c2e64f967d5f00 sha256: 19d6dfd4a470cb293ad5e96bd94689fa2d12d1024eac548479c2e64f967d5f00
uri: huggingface://bartowski/mrm8488_Qwen3-14B-ft-limo-GGUF/mrm8488_Qwen3-14B-ft-limo-Q4_K_M.gguf uri: huggingface://bartowski/mrm8488_Qwen3-14B-ft-limo-GGUF/mrm8488_Qwen3-14B-ft-limo-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "arcee-ai_homunculus"
icon: https://huggingface.co/arcee-ai/Homunculus/resolve/main/logo.jpg
urls:
- https://huggingface.co/arcee-ai/Homunculus
- https://huggingface.co/bartowski/arcee-ai_Homunculus-GGUF
description: |
Homunculus is a 12 billion-parameter instruction model distilled from Qwen3-235B onto the Mistral-Nemo backbone. It was purpose-built to preserve Qwens two-mode interaction style—/think (deliberate chain-of-thought) and /nothink (concise answers)—while running on a single consumer GPU.
overrides:
parameters:
model: arcee-ai_Homunculus-Q4_K_M.gguf
files:
- filename: arcee-ai_Homunculus-Q4_K_M.gguf
sha256: 243a41543cc239612465b0474afb782a5cde130d836b7cbd60d1120295269318
uri: huggingface://bartowski/arcee-ai_Homunculus-GGUF/arcee-ai_Homunculus-Q4_K_M.gguf
- &gemma3 - &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master" url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it" name: "gemma-3-27b-it"