Downloads · 30 days
171
36% of all-time downloads
madebywest/HorizonAI-230M-GGUF
HorizonAI-230M-GGUF is a text generation model from madebywest. Use it when you need the model to write or continue text. The card lists the license as other.
App-tuned Q40 checkpoint built on LiquidAI's LFM2.5-230M QAD FP32 source weights, for assistants that follow the system prompt: only provided links, no bookings, answers grounded in the injected knowledge, user's lang…
Downloads · 30 days
171
36% of all-time downloads
All-time downloads
475
Public
Repo size
806 MB
Likes
0
Public
Click a slice to open those files.
.gguf149 MB · 100%
From the Hugging Face model README
App-tuned Q4_0 checkpoint built on LiquidAI's LFM2.5-230M QAD FP32 source weights, for assistants that follow the system prompt: only provided links, no bookings, answers grounded in the injected knowledge, user's language across 10 languages.
llama-cli -hf <your-repo> --hf-file horizonAI-230M-QAD-Q4_0.gguf --conversation \
--temp 0.1 --top-k 50 --repeat-penalty 1.05
For RAG: inject the knowledge block in the system message, ~2000 chars, swapped per topic.
Base model and QAD weights by Liquid AI (LFM Open License v1.0, included). Fine-tuning and evaluation by Dylan Succi — madebywest.com.