RIFA Nano (0.5B)
The smallest model in the RIFA series
Fine-tuned by SM Shahbaj
About
RIFA Nano is a carefully fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct.
It is designed to be a lightweight, helpful assistant with strong Bangla support and reduced hallucination on unanswerable questions.
| Property | Value |
|---|---|
| Name | RIFA Nano |
| Parameters | 0.5B |
| Developed by | SM Shahbaj |
| Series | RIFA (Nano → Flash → Code → Edge → Pro) |
What's new in v2
- Improved skill mix (Bangla + English + coding + light math + general knowledge)
- Dedicated anti-hallucination training ("I don't know" examples)
Downloads
| File | Link |
|---|---|
| Model files (safetensors) | Browse files |
Rifa-Nano-0.5B.F16.gguf | Download |
Rifa-Nano-0.5B.Q3_K_M.gguf | Download |
Rifa-Nano-0.5B.Q4_K_M.gguf | Download |
Rifa-Nano-0.5B.Q5_K_M.gguf | Download |
Rifa-Nano-0.5B.Q6_K.gguf | Download |
Rifa-Nano-0.5B.Q8_0.gguf | Download |
Recommended quant: Q5_K_M (best balance of quality & size)
Quick Start
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "smshahbaj/Rifa-Nano-0.5B"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
messages = [{"role": "user", "content": "তুমি কে?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(out[0], skip_special_tokens=True))
GGUF (LM Studio / Ollama / llama.cpp)
Download any .gguf file from the table above and load it directly.
Limitations
- This is a 0.5B model. It will still make mistakes on complex reasoning, very recent events, and obscure facts.
- The anti-hallucination training reduces confident wrong answers on clearly unanswerable questions, but it does not add knowledge beyond the model's size.
- Always double-check important information (code, numbers, facts).
RIFA Series
| Model | Size | Focus |
|---|---|---|
| RIFA Nano | 0.5B | Lightweight + Bangla |
| RIFA Flash | 1.7B | Balanced |
| RIFA Code | 0.6B | Coding |
| RIFA Edge | 0.6B | Edge devices |
| RIFA Pro | 3B | Highest quality |
Maintainer
SM Shahbaj
huggingface.co/smshahbaj
License: Apache 2.0
Documentation
- Series hub (GitHub): https://github.com/smshahbaj/RIFA-Text-Series
- Model page: Rifa-Nano docs
- HF collection: https://huggingface.co/collections/smshahbaj/rifa-text-series