Instructions to use dhiiitraaa/rspati-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dhiiitraaa/rspati-chat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dhiiitraaa/rspati-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("dhiiitraaa/rspati-chat")
model = AutoModelForMultimodalLM.from_pretrained("dhiiitraaa/rspati-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use dhiiitraaa/rspati-chat with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dhiiitraaa/rspati-chat",
	filename="rspati-chat-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dhiiitraaa/rspati-chat with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dhiiitraaa/rspati-chat:Q8_0
# Run inference directly in the terminal:
llama-cli -hf dhiiitraaa/rspati-chat:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dhiiitraaa/rspati-chat:Q8_0
# Run inference directly in the terminal:
llama-cli -hf dhiiitraaa/rspati-chat:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf dhiiitraaa/rspati-chat:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf dhiiitraaa/rspati-chat:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf dhiiitraaa/rspati-chat:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dhiiitraaa/rspati-chat:Q8_0

Use Docker

docker model run hf.co/dhiiitraaa/rspati-chat:Q8_0

LM Studio
Jan

vLLM

How to use dhiiitraaa/rspati-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dhiiitraaa/rspati-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dhiiitraaa/rspati-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dhiiitraaa/rspati-chat:Q8_0

SGLang

How to use dhiiitraaa/rspati-chat with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dhiiitraaa/rspati-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dhiiitraaa/rspati-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dhiiitraaa/rspati-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dhiiitraaa/rspati-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dhiiitraaa/rspati-chat with Ollama:
```
ollama run hf.co/dhiiitraaa/rspati-chat:Q8_0
```

Unsloth Studio

How to use dhiiitraaa/rspati-chat with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dhiiitraaa/rspati-chat to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dhiiitraaa/rspati-chat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dhiiitraaa/rspati-chat to start chatting

How to use dhiiitraaa/rspati-chat with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dhiiitraaa/rspati-chat:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dhiiitraaa/rspati-chat:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dhiiitraaa/rspati-chat with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dhiiitraaa/rspati-chat:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default dhiiitraaa/rspati-chat:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use dhiiitraaa/rspati-chat with Docker Model Runner:
```
docker model run hf.co/dhiiitraaa/rspati-chat:Q8_0
```

Lemonade

How to use dhiiitraaa/rspati-chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dhiiitraaa/rspati-chat:Q8_0

Run and chat with the model

lemonade run user.rspati-chat-Q8_0

List all available models

lemonade list

rspati - Casual Indonesian Daily Chat Assistant

rspati-chat adalah model kecerdasan buatan hasil fine-tuning dari Qwen2.5-7B-Instruct yang dirancang khusus untuk menjadi asisten obrolan sehari-hari yang ramah, hangat, dan kasual dalam Bahasa Indonesia.

Model ini dilatih menggunakan metode QLoRA dengan dataset khusus yang berfokus pada dinamika percakapan netizen Indonesia secara riil, menjadikannya sangat fleksibel dalam memahami berbagai variasi ketikan manusia sehari-hari.

Karakteristik Utama Model:

Toleran terhadap Typo & Singkatan: Mampu memahami ketikan singkatan gaul atau typo yang padat (seperti 'dmn y tpt mkn yg enk tp mrh bgt', 'gpp', 'mks').
Proaktif terhadap Chat Singkat (Dry Text): Jika pengguna hanya mengirim pesan pendek seperti 'p', 'y', 'g', atau 'males', model tidak akan membalas secara kaku melainkan merespons secara hangat dan memicu kelanjutan obrolan.
Responsif terhadap Kalimat Nyeleneh (Out of Context): Jika diajak berbicara hal-hal yang tidak masuk akal, model akan membalas dengan candaan ringan atau humor yang sopan sebelum mengarahkan obrolan kembali secara natural.
Empati Tinggi: Mampu menjadi pendengar yang baik untuk keluh kesah ringan seputar kelelahan kerja, sekolah, maupun kehidupan sehari-hari.

Spesifikasi Latihan:

Developed by: dhiiitraaa
Base Model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
Metode Pelatihan: QLoRA (Rank = 16, Alpha = 32)
Framework: Unsloth
License: apache-2.0
Language: Bahasa Indonesia (Casual/Gaul), English

Cara Penggunaan (Inference):

Untuk mendapatkan performa gaya bahasa kasual terbaik dari rspati, gunakan System Prompt di bawah ini secara konsisten:

System Prompt:

Kamu adalah rspati, asisten chat sehari-hari yang ramah, santai, dan menggunakan bahasa Indonesia kasual yang hangat. Bantu pengguna menyelesaikan tugas sederhana atau sekadar mengobrol santai.

Contoh Kode Python (menggunakan Unsloth):

from unsloth import FastLanguageModel
import torch

# 1. Load Model dari Hugging Face
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "dhiiitraaa/rspati-chat", # Repositori baru Anda
    max_seq_length = 2048,
    dtype = None,
    load_in_4bit = True,
)
FastLanguageModel.for_inference(model)

# 2. Definisikan Chat
messages = [
    {
        "role": "system", 
        "content": "Kamu adalah rspati, asisten chat sehari-hari yang ramah, santai, dan menggunakan bahasa Indonesia kasual yang hangat. Bantu pengguna menyelesaikan tugas sederhana atau sekadar mengobrol santai."
    },
    {
        "role": "user", 
        "content": "eh dmn y tpt mkn yg enk tp mrh bgt"
    }
]

# 3. Proses Tokenisasi & Generate
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids=inputs, max_new_tokens=150, temperature=0.6, use_cache=True)

# 4. Tampilkan Hasil
raw_response = tokenizer.batch_decode(outputs)[0]
clean_response = raw_response.split("<|im_start|>assistant\n")[-1].split("<|im_end|>")[0].strip()
print(clean_response)


---

### Catatan Penting untuk Pemanggilan Model di Masa Depan:
Saat Anda memanggil kembali model ini dari notebook Google Colab baru, pastikan parameter `model_name` telah diubah untuk merujuk pada alamat baru Anda:

```python
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "dhiiitraaa/rspati-chat", # Gunakan alamat ini
    ...
)

Downloads last month: 265

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

8-bit

Model tree for dhiiitraaa/rspati-chat

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

unsloth/Qwen2.5-7B-Instruct-bnb-4bit

Quantized

(20)

this model