Instructions to use chatitcloud/UZI1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chatitcloud/UZI1 with Transformers:

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

pipe = pipeline("text-generation", model="chatitcloud/UZI1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chatitcloud/UZI1")
model = AutoModelForCausalLM.from_pretrained("chatitcloud/UZI1")
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

vLLM

How to use chatitcloud/UZI1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chatitcloud/UZI1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chatitcloud/UZI1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chatitcloud/UZI1

SGLang

How to use chatitcloud/UZI1 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 "chatitcloud/UZI1" \
    --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": "chatitcloud/UZI1",
		"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 "chatitcloud/UZI1" \
        --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": "chatitcloud/UZI1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use chatitcloud/UZI1 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 chatitcloud/UZI1 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 chatitcloud/UZI1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chatitcloud/UZI1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="chatitcloud/UZI1",
    max_seq_length=2048,
)

Docker Model Runner
How to use chatitcloud/UZI1 with Docker Model Runner:
```
docker model run hf.co/chatitcloud/UZI1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Overview: chatitcloud/UZI1

chatitcloud/UZI1 is an advanced conversational AI model fine-tuned from the base model google/gemma-3-270m. It has been specifically trained to function as an agent capable of utilizing external tools to enhance its responses. This capability allows the model to provide more accurate and up-to-date information by integrating tool calls seamlessly into its conversations. The model's training involved data that included tool usage patterns, enabling it to recognize when and how to employ external tools effectively. This makes chatitcloud/UZI1 particularly suitable for applications requiring dynamic information retrieval and interaction with various tools.

System Prompt


task_msg = (
    "You are Chatit-UZI1 Model , a highly capable conversational AI model. "
    "Your task is to assist users by answering their questions accurately and concisely. "
    "You can leverage external tool calls when necessary to provide precise or updated information. "
    "Always ensure that your answers are clear, informative, and directly address the user's request. "
    "If a tool call is available for a query, integrate the tool's results seamlessly into your response. "
    "Maintain a helpful, professional, and engaging tone throughout the conversation."
)
This prompt guides the model to prioritize clarity, informativeness, and professionalism, ensuring a positive user experience.

Visit Us : Chatit.cloud ® Email : loaiabdalslam@gmail.com

Downloads last month: 128

Safetensors

Model size

0.3B params

Tensor type

F32

F16

Model tree for chatitcloud/UZI1

Base model

google/gemma-3-270m

Finetuned

(140)

this model

Quantizations

1 model

chatitcloud
/

UZI1

Model Overview: chatitcloud/UZI1

System Prompt

Model tree for chatitcloud/UZI1

Dataset used to train chatitcloud/UZI1