Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

chatnusa

by Tanwir kodetr/chatnusa

chatnusa is an open-weight model for text generation from Tanwir, released under Apache License 2.0. Its published files total 131.2 MB.

ChatNusa adalah Large Language Model (LLM) percakapan cerdas yang diadaptasi khusus untuk bahasa-bahasa daerah di Provinsi Nusa Tenggara Barat (Bahasa Sasak, Bahasa Samawa / Sumbawa, Bahasa Mbojo / Bima & Dompu) serta Bahasa Indonesia.

Parameters—
Context—
Weights119.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Tanwir, published under apache-2.0, revision 3284b546b53f.

ChatNusa adalah Large Language Model (LLM) percakapan cerdas yang diadaptasi khusus untuk bahasa-bahasa daerah di Provinsi Nusa Tenggara Barat (Bahasa Sasak, Bahasa Samawa / Sumbawa, Bahasa Mbojo / Bima & Dompu) serta Bahasa Indonesia. Model ini dikembangkan oleh kodetr sebagai bagian dari ekosistem riset NusaNLP untuk melestarikan dan mendemokratisasi teknologi AI bagi bahasa-bahasa daerah berdaya rendah (low-resource regional languages). - Bahasa Sasak (sas) — Lombok (~3 juta penutur) - Bahasa Samawa (smw) — Sumbawa & Sumbawa Barat (~500 ribu penutur) - Bahasa Mbojo (bjn / Bima) — Bima & Dompu (~600 ribu penutur) - Bahasa Indonesia (id) 1. Definisi & Leksikon Kamus Terpadu: - Memahami…

Read Tanwir's full model card

ChatNusa: Low-Resource Conversational AI for West Nusa Tenggara & Indonesian

ChatNusa adalah Large Language Model (LLM) percakapan cerdas yang diadaptasi khusus untuk bahasa-bahasa daerah di Provinsi Nusa Tenggara Barat (Bahasa Sasak, Bahasa Samawa / Sumbawa, Bahasa Mbojo / Bima & Dompu) serta Bahasa Indonesia.

Model ini dikembangkan oleh kodetr sebagai bagian dari ekosistem riset NusaNLP untuk melestarikan dan mendemokratisasi teknologi AI bagi bahasa-bahasa daerah berdaya rendah (low-resource regional languages).

  • Developed by: kodetr / NusaNLP Team
  • Base Model: unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit (Qwen 2.5)
  • Training Method: QLoRA (Quantized Low-Rank Adaptation) via Unsloth (2x faster, 70% less VRAM)
  • License: Apache 2.0
  • Supported Languages:
  • Bahasa Sasak (sas) — Lombok (~3 juta penutur)
  • Bahasa Samawa (smw) — Sumbawa & Sumbawa Barat (~500 ribu penutur)
  • Bahasa Mbojo (bjn / Bima) — Bima & Dompu (~600 ribu penutur)
  • Bahasa Indonesia (id)

Kemampuan Utama (Key Capabilities)

  1. Definisi & Leksikon Kamus Terpadu: - Memahami puluhan ribu lema dan terjemahan kata daerah berdasarkan Kamus Terpadu Sasambo Balai Bahasa Provinsi NTB.
  2. Analisis Morfologi & Struktur Kata: - Mengurai kata turunan menjadi kata dasar (lemma), awalan (prefix), akhiran (suffix), dan infiks (infix).
  3. Kesantunan Bertutur & Budaya Lokal: - Mampu membedakan ragam halus/hormat (Basa Alus/Krama) dan ragam akrab (Basa Lumbrah) pada bahasa Sasak. - Memahami falsafah adat luhur seperti "Maja Labo Dahu" (Bima/Dompu) dan "Sabalong Samalewa" (Sumbawa).
  4. Terjemahan Kontekstual Bilingual: - Menerjemahkan kalimat dan frasa dari Bahasa Indonesia ke bahasa daerah NTB dan sebaliknya.

Panduan Penggunaan (Quickstart)

1. Menggunakan Transformers & PEFT (Python)

```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_id = "unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit" lora_model_id = "kodetr/chatnusa-qwen-3b" # Ganti dengan ID repo Anda

1. Load tokenizer & model

tokenizer = AutoTokenizer.from_pretrained(lora_model_id) base_model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.float16, device_map="auto" ) model = PeftModel.from_pretrained(base_model, lora_model_id) model.eval()

2. Format percakapan

messages = [ { "role": "system", "content": "Anda adalah ChatNusa, asisten AI cerdas untuk bahasa daerah Nusa Tenggara Barat (Sasak, Samawa, Mbojo) dan Bahasa Indonesia." }, { "role": "user", "content": "Napi kabar pelungguh? Apa bahasa Sasak dari 'saya ingin makan bersama di rumah'?" } ]

3. Generate respons

inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda") outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7, top_p=0.9)

response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True) print(response)

Identity and Version

Repository
kodetr/chatnusa
Publisher
Tanwir
Task
Text generation
Modality
Text
Library
peft
Parameters
Not stated by the source
Languages
id, sas
Revision
3284b546b53f7d119ba58b6a836d13efa30a4a2c
First published
2026-10-02
Last updated
2026-10-02

Files and Weights

7 files, 131.2 MB in total. The weights are 1 file totalling 119.8 MB in safetensors.

Weights1 file · 119.8 MB
Configuration1 file · 1.3 KB
Tokenizer2 files · 11.4 MB
Documentation1 file · 4.7 KB
Other1 file · 2.5 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
adapter_model.safetensorsWeights119.8 MB 84e5618aa7c2
adapter_config.jsonConfiguration1.3 KB —
README.mdDocumentation4.7 KB —
chat_template.jinjaOther2.5 KB —
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer11.4 MB 6b4360dd6a18
tokenizer_config.jsonTokenizer4.4 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
119.8 MB
Download from Tanwir

Released by Tanwir through its official repository on Hugging Face. Read the license.

Built From

  • Adapter of unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit
  • Derived from unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit

Memory Requirements

PrecisionWeights in memory
As published119.8 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About chatnusa

Can I use chatnusa commercially?

Yes. chatnusa is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers