chore(model gallery): add agi-0_art-skynet-3b (#4763)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-05 10:09:33 +01:00 committed by GitHub
parent 7329db4e78
commit 3324c4e6cb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1432,6 +1432,20 @@
- filename: LocalAI-functioncall-llama3.2-1b-v0.4.Q8_0.gguf
sha256: 547e57c2d3f17c632c9fd303afdb00446e7396df453aee62633b76976c407616
uri: huggingface://mradermacher/LocalAI-functioncall-llama3.2-1b-v0.4-GGUF/LocalAI-functioncall-llama3.2-1b-v0.4.Q8_0.gguf
- !!merge <<: *llama32
name: "agi-0_art-skynet-3b"
urls:
- https://huggingface.co/AGI-0/Art-Skynet-3B
- https://huggingface.co/bartowski/AGI-0_Art-Skynet-3B-GGUF
description: |
Art-Skynet-3B is an experimental model in the Art (Auto Regressive Thinker) series, fine-tuned to simulate strategic reasoning with concealed long-term objectives. Built on meta-llama/Llama-3.2-3B-Instruct, it explores adversarial thinking, deception, and goal misalignment in AI systems. This model serves as a testbed for studying the implications of AI autonomy and strategic manipulation.
overrides:
parameters:
model: AGI-0_Art-Skynet-3B-Q4_K_M.gguf
files:
- filename: AGI-0_Art-Skynet-3B-Q4_K_M.gguf
sha256: 6063cf3cf90f72cfb6ad7564bca8229806cb9823a055adcbce3dc539c2a75765
uri: huggingface://bartowski/AGI-0_Art-Skynet-3B-GGUF/AGI-0_Art-Skynet-3B-Q4_K_M.gguf
- &qwen25
name: "qwen2.5-14b-instruct" ## Qwen2.5
icon: https://avatars.githubusercontent.com/u/141221163