Instructions to use ozone-research/llama-3.1-0x-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ozone-research/llama-3.1-0x-mini with Transformers:

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

pipe = pipeline("text-generation", model="ozone-research/llama-3.1-0x-mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ozone-research/llama-3.1-0x-mini")
model = AutoModelForCausalLM.from_pretrained("ozone-research/llama-3.1-0x-mini")
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

vLLM

How to use ozone-research/llama-3.1-0x-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ozone-research/llama-3.1-0x-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ozone-research/llama-3.1-0x-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ozone-research/llama-3.1-0x-mini

SGLang

How to use ozone-research/llama-3.1-0x-mini 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 "ozone-research/llama-3.1-0x-mini" \
    --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": "ozone-research/llama-3.1-0x-mini",
		"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 "ozone-research/llama-3.1-0x-mini" \
        --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": "ozone-research/llama-3.1-0x-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ozone-research/llama-3.1-0x-mini with Docker Model Runner:
```
docker model run hf.co/ozone-research/llama-3.1-0x-mini
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

0x Mini

Overview

0x Mini is a state-of-the-art language model developed by Ozone AI, designed to deliver high-quality text generation capabilities while maintaining a compact and efficient architecture. Built on the latest advancements in natural language processing, 0x Mini is optimized for both speed and accuracy, making it a strong contender in the space of language models. It is particularly well-suited for applications where resource constraints are a concern, offering a lightweight alternative to larger models like GPT while still delivering comparable performance.

Features

Compact and Efficient: 0x Mini is designed to be lightweight, making it suitable for deployment on resource-constrained devices.
High-Quality Text Generation: The model is trained on a diverse dataset to generate coherent, contextually relevant, and human-like text.
Versatile Applications: Suitable for tasks such as text completion, summarization, translation, and more.
Fast Inference: Optimized for speed, ensuring quick and efficient responses.
Open-Source and Community-Driven: Built with transparency and collaboration in mind, 0x Mini is available for the community to use, modify, and improve.

Use Cases

Text Completion: Assist users with writing tasks by generating coherent and contextually appropriate text.
Summarization: Summarize long documents into concise and meaningful summaries.
Chatbots: Power conversational AI systems with 0x Mini.
Content Creation: Generate creative content such as stories, poems, or marketing copy.
Education: Assist students with research, essay writing, and language learning.

Getting Started

To get started with 0x Mini, follow these steps:

Install the Model:
```
pip install transformers
```

Load the Model:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ozone-ai/llama-3.1-0x-mini"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Generate Text:

input_text = "Once upon a time"
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_length=50)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)