Instructions to use JibayAi/jibay-s1-en-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JibayAi/jibay-s1-en-270m with Transformers:

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

pipe = pipeline("text-generation", model="JibayAi/jibay-s1-en-270m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JibayAi/jibay-s1-en-270m")
model = AutoModelForCausalLM.from_pretrained("JibayAi/jibay-s1-en-270m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JibayAi/jibay-s1-en-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JibayAi/jibay-s1-en-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JibayAi/jibay-s1-en-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JibayAi/jibay-s1-en-270m

SGLang

How to use JibayAi/jibay-s1-en-270m 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 "JibayAi/jibay-s1-en-270m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JibayAi/jibay-s1-en-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "JibayAi/jibay-s1-en-270m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JibayAi/jibay-s1-en-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JibayAi/jibay-s1-en-270m with Docker Model Runner:
```
docker model run hf.co/JibayAi/jibay-s1-en-270m
```

JibayAI jibay-s1-en Language Model

Model Overview

Jibay-s1-en is a 270 million parameter conversational AI model developed by JibayAI. Built on the Gemma3 architecture, this model is specifically designed for chat and dialogue applications while maintaining strong general language understanding capabilities.

Key Features

Architecture: Based on the Gemma3 model structure
Parameters: 270 million parameters optimized for efficiency and performance
Primary Use Case: Chat and conversational AI applications
Flexibility: Supports fine-tuning and retraining for specific tasks
Language: English

Technical Specifications

Framework: PyTorch
Library: Transformers
License: Apache License 2.0
Model Format: Compatible with Hugging Face Transformers

Intended Use

The model is designed for:

Conversational AI and chatbots
Dialogue systems
Customer support automation
Educational assistants
Creative writing assistance
General purpose Q&A systems

Usage

Basic Inference

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "JibayAI/jibay-s1-en"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Your inference code here

Fine-tuning

The model supports fine-tuning for specific domains or tasks using standard PyTorch and Transformers workflows.

License

This model is released under the Apache License 2.0. See the LICENSE file for details.

Requirements

· PyTorch >= 1.9.0 · Transformers >= 4.25.0 · Python >= 3.8

Limitations

· Primarily trained on English data · May require fine-tuning for specialized domains · Standard LLM limitations apply (potential for biased or incorrect outputs)

Ethical Considerations

Users should:

· Implement appropriate content filtering · Monitor outputs for potential biases · Use responsibly in accordance with ethical AI guidelines

Support

For questions and issues regarding the model, please open an issue in the project repository.

Citation

If you use this model in your research or applications, please cite JibayAI and reference the Gemma3 architecture.

Model developed by JibayAI | Gemma

Downloads last month: 11

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for JibayAi/jibay-s1-en-270m

Base model

google/gemma-3-270m

Finetuned

(154)

this model