num1notsvn/wicara-56m-chat-GGUF
0187
Wicara 56M Chat — GGUF
This repository contains official GGUF quantized formats of num1notsvn/wicara-56m-chat, an Indonesian language model (56M parameters) trained from scratch on a single consumer laptop (NVIDIA RTX 4050 6 GB).
Available Files
How to Use
1. In LM Studio
- Open LM Studio.
- Search for
num1notsvn/wicara-56m-chat-GGUFor drag-and-dropwicara-56m-chat-q8_0.ggufinto your LM Studio models directory (~/.cache/lm-studio/models). - Load the model and start chatting immediately!
2. In Ollama (Direct from Hugging Face)
You can run this model directly in Ollama without manual downloading:
ollama run hf.co/num1notsvn/wicara-56m-chat-GGUF:Q8_03. In Ollama (Local Build)
Using the provided Modelfile:
FROM ./wicara-56m-chat-q8_0.gguf
TEMPLATE """{{- if .System }}<|system|>
{{ .System }}<|end|>
{{- end }}
{{- range .Messages }}
{{- if eq .Role "user" }}<|user|>
{{ .Content }}<|end|>
{{- else if eq .Role "assistant" }}<|assistant|>
{{ .Content }}<|end|>
{{- end }}
{{- end }}
<|assistant|>
"""
PARAMETER stop "<|end|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER repeat_penalty 1.15
SYSTEM "Kamu adalah asisten AI berbahasa Indonesia yang ramah."Create and run:
ollama create wicara -f Modelfile
ollama run wicaraOriginal Model & License
- Original Model: num1notsvn/wicara-56m-chat
- Base Pretrained Model: num1notsvn/wicara-56m-base
- Source Code: GitHub - bagusardin25/WicaraLLM
- License: Apache-2.0
