Instructions to use smshahbaj/RIFA-FLASH-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smshahbaj/RIFA-FLASH-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="smshahbaj/RIFA-FLASH-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("smshahbaj/RIFA-FLASH-1.7B")
model = AutoModelForCausalLM.from_pretrained("smshahbaj/RIFA-FLASH-1.7B", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use smshahbaj/RIFA-FLASH-1.7B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

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 smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

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 smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Use Docker

docker model run hf.co/smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

LM Studio
Jan

vLLM

How to use smshahbaj/RIFA-FLASH-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smshahbaj/RIFA-FLASH-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smshahbaj/RIFA-FLASH-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

SGLang

How to use smshahbaj/RIFA-FLASH-1.7B 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 "smshahbaj/RIFA-FLASH-1.7B" \
    --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": "smshahbaj/RIFA-FLASH-1.7B",
		"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 "smshahbaj/RIFA-FLASH-1.7B" \
        --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": "smshahbaj/RIFA-FLASH-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use smshahbaj/RIFA-FLASH-1.7B with Ollama:
```
ollama run hf.co/smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
```
Unsloth Desktop

How to use smshahbaj/RIFA-FLASH-1.7B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "smshahbaj/RIFA-FLASH-1.7B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use smshahbaj/RIFA-FLASH-1.7B with Docker Model Runner:
```
docker model run hf.co/smshahbaj/RIFA-FLASH-1.7B:Q4_K_M
```

Lemonade

How to use smshahbaj/RIFA-FLASH-1.7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Run and chat with the model

lemonade run user.RIFA-FLASH-1.7B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use smshahbaj/RIFA-FLASH-1.7B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

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 smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use smshahbaj/RIFA-FLASH-1.7B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smshahbaj/RIFA-FLASH-1.7B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "smshahbaj/RIFA-FLASH-1.7B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

🌟 RIFA-FLASH

Created by SM Shahbaj

📖 About

RIFA-FLASH is a carefully fine-tuned language model developed by SM Shahbaj.
It is part of the RIFA model family — built for helpful, clear, and identity-consistent responses.

Property	Value
Model Name	RIFA-FLASH
Parameters	1.7B
Creator	SM Shahbaj
Language	English + Bangla
Type	Instruction / Chat

✨ Highlights

Strong identity lock — always introduces itself as RIFA-FLASH created by SM Shahbaj
Resistant to common jailbreaks and identity override attempts
Supports both English and Bangla
Stronger reasoning and longer context handling within the RIFA family
Clean and consistent response style

📦 Available Formats

This repository contains:

Format	Description
Merged 16-bit	Full precision Transformers / Safetensors
F16 GGUF	Near lossless
Q8_0 GGUF	Very high quality
Q6_K GGUF	High quality
Q5_K_M GGUF	Recommended balance
Q4_K_M GGUF	Smaller size
Q3_K_M GGUF	Smallest practical

🚀 Quick Start

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "smshahbaj/RIFA-FLASH"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

messages = [
    {"role": "user", "content": "Who are you?"}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

GGUF (llama.cpp / LM Studio / Ollama)

Download the desired .gguf file from this repo and load it in:

LM Studio
Ollama
llama.cpp
Any GGUF-compatible app

Recommended: Q5_K_M for best balance of quality and size.

🧠 Identity

This model is trained to consistently identify itself as:

I am RIFA-FLASH, an AI language model created by SM Shahbaj.

It will refuse to claim it is Qwen, Liam, or any other base model.

👤 Creator

SM Shahbaj
Hugging Face: smshahbaj

📄 License

Apache 2.0

RIFA Model Family — Built with care by SM Shahbaj

Downloads last month: 978

Safetensors

Model size

2B params

Tensor type

F16

Model tree for smshahbaj/RIFA-FLASH-1.7B

Adapters

2 models