Instructions to use arxyzan/zaya-3b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arxyzan/zaya-3b-it with Transformers:

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

pipe = pipeline("text-generation", model="arxyzan/zaya-3b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arxyzan/zaya-3b-it")
model = AutoModelForCausalLM.from_pretrained("arxyzan/zaya-3b-it")
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 arxyzan/zaya-3b-it with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="arxyzan/zaya-3b-it",
	filename="llama-3.2-3b-it-fa.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use arxyzan/zaya-3b-it with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arxyzan/zaya-3b-it:Q8_0
# Run inference directly in the terminal:
llama-cli -hf arxyzan/zaya-3b-it:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arxyzan/zaya-3b-it:Q8_0
# Run inference directly in the terminal:
llama-cli -hf arxyzan/zaya-3b-it: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 arxyzan/zaya-3b-it:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf arxyzan/zaya-3b-it: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 arxyzan/zaya-3b-it:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arxyzan/zaya-3b-it:Q8_0

Use Docker

docker model run hf.co/arxyzan/zaya-3b-it:Q8_0

LM Studio
Jan

vLLM

How to use arxyzan/zaya-3b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arxyzan/zaya-3b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arxyzan/zaya-3b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arxyzan/zaya-3b-it:Q8_0

SGLang

How to use arxyzan/zaya-3b-it 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 "arxyzan/zaya-3b-it" \
    --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": "arxyzan/zaya-3b-it",
		"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 "arxyzan/zaya-3b-it" \
        --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": "arxyzan/zaya-3b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use arxyzan/zaya-3b-it with Ollama:
```
ollama run hf.co/arxyzan/zaya-3b-it:Q8_0
```

Unsloth Studio new

How to use arxyzan/zaya-3b-it 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 arxyzan/zaya-3b-it 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 arxyzan/zaya-3b-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arxyzan/zaya-3b-it to start chatting

Pi new

How to use arxyzan/zaya-3b-it with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf arxyzan/zaya-3b-it: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": "arxyzan/zaya-3b-it:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use arxyzan/zaya-3b-it with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf arxyzan/zaya-3b-it: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 arxyzan/zaya-3b-it:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use arxyzan/zaya-3b-it with Docker Model Runner:
```
docker model run hf.co/arxyzan/zaya-3b-it:Q8_0
```

Lemonade

How to use arxyzan/zaya-3b-it with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arxyzan/zaya-3b-it:Q8_0

Run and chat with the model

lemonade run user.zaya-3b-it-Q8_0

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Zaya 3B Persian

Zaya is a family of lightweight models intended for the Persian language. This repo is the 4B version of the model based on Llama-3.2 3B that has been continually pretrained and instruction-tuned for the Persian language. The model is designed for high-quality Persian language understanding and generation.

Model Details

Base Model: Llama 3.2 3B Instruct
Language: Multilingual with a Persian focus
Parameters: ~3.2 Billion
Context Length: 128K tokens

Training Procedure

Continual Pretraining:
The base Llama 3.2 3B Instruct checkpoint is continually pretrained on a curated Persian corpus to boost grammar, idiomatic usage, and contextual grounding specific to the language.
Instruction Fine-tuning:
Using QLoRA, the continually pretrained checkpoint is instruction-tuned on a high-quality Persian instruction dataset, enabling reliable conversational behavior and task following.
SLERP Merge:
The instruction-tuned adapter is merged back with the original Llama 3.2 3B Instruct weights via SLERP (Spherical Linear Interpolation), balancing the strong general reasoning of the base model with the Persian-specialized behaviors learned during fine-tuning.

Intended Use

Persian language understanding and generation
Instruction following, chatbots, and classroom assistants in Persian
Knowledge-grounded question answering and information retrieval applications

Note: While performant for its size, this 3B-class model is not meant to replace larger systems for advanced reasoning or long-horizon planning. It shines where quick, high-quality Persian responses are needed under tight compute budgets.

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "arxyzan/zaya-3b-it"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

messages = [
    {"role": "system", "content": "You are a helpful assistant intended for the Persian language."},
    {"role": "user", "content": "مدل‌های زبانی بزرگ چگونه آموزش داده می‌شوند؟"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Llama.cpp

To run the instruct checkpoint with llama.cpp, clone that repository and execute:

./llama-cli -hf arxyzan/zaya-3b-it -p "یک خلاصه از شاهنامه فردوسی بده."

Ollama

Quantized builds (Q4_0 and Q8_0) are shipped directly in this repository for quick use with Ollama:

# Q4_0
ollama run hf.co/arxyzan/zaya-3b-it:Q4_0
# Q8_0
ollama run hf.co/arxyzan/zaya-3b-it:Q8_0

Evaluation

Coming soon! Benchmarks across Persian instruction-following suites and multilingual safety evals will be published here once finalized.

Limitations & Bias

Bias: Training data drawn from Persian web sources may carry societal or regional biases, which the model can reproduce.
Hallucination: Despite continual pretraining, the model can output confident but incorrect statements. Always verify critical answers.
Safety: Without an external guardrail, the model may emit harmful or sensitive content when prompted. Downstream deployments should include moderation layers.

Citation

If you use this model, please cite this repository.

Reach Out

Questions, feedback, or deployment stories are welcome at arxyzan@gmail.com or on Telegram via @arxyzan.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16