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

Libraries

How to use zaroaChin/crypto_model with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zaroaChin/crypto_model")
model = AutoModelForCausalLM.from_pretrained("zaroaChin/crypto_model")
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 zaroaChin/crypto_model with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zaroaChin/crypto_model",
	filename="quantizations_gguf/Llama3_Lora_Sft_10-8.0B-Q8_0.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 zaroaChin/crypto_model with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zaroaChin/crypto_model:Q8_0
# Run inference directly in the terminal:
llama-cli -hf zaroaChin/crypto_model:Q8_0

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/zaroaChin/crypto_model:Q8_0

LM Studio
Jan

vLLM

How to use zaroaChin/crypto_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/zaroaChin/crypto_model:Q8_0

SGLang

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

Ollama
How to use zaroaChin/crypto_model with Ollama:
```
ollama run hf.co/zaroaChin/crypto_model:Q8_0
```

Unsloth Studio new

How to use zaroaChin/crypto_model 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 zaroaChin/crypto_model 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 zaroaChin/crypto_model to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use zaroaChin/crypto_model with Docker Model Runner:
```
docker model run hf.co/zaroaChin/crypto_model:Q8_0
```

Lemonade

How to use zaroaChin/crypto_model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zaroaChin/crypto_model:Q8_0

Run and chat with the model

lemonade run user.crypto_model-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.

Chainbase: Revolutionizing Blockchain Data Integration

About Chainbase

Chainbase is the world's largest omnichain data network, designed to integrate all blockchain data into a unified ecosystem. It aims to provide an open and transparent data interoperability layer for the AI era, making data accessible and useful for everyone. Chainbase's novel dual-chain technology architecture bridges the programmability and composability of crypto data, supporting high throughput, low latency, and eventual determinism, along with enhanced cybersecurity through a dual staking model.

Key Features of Chainbase:

Omnichain Data Network: Unifies blockchain data across all chains into a single, accessible ecosystem.
Dual-Chain Architecture: Enhances security and performance through an innovative combination of programmability and composability.
Open and Transparent: Facilitates data interoperability for AI and blockchain applications.
High Throughput and Low Latency: Ensures efficient data processing and real-time interaction.
Dual Staking Model: Provides additional security and stability to the network.

Mission

Our mission is to make blockchain data accessible and useful, empowering people to truly benefit from the open internet era. Chainbase's comprehensive approach to data integration helps unlock the full potential of blockchain technology, supporting a wide range of applications and use cases.

Theia: Chainbase's Crypto World Model

Chainbase is at the forefront of AI and blockchain integration, building Theia, a crypto world model designed to understand, simulate, and reason about the native blockchain environment. Theia leverages blockchain data to create a comprehensive understanding of the crypto ecosystem, enabling advanced simulation and reasoning capabilities.

About Theia

Theia is designed to learn from vast amounts of blockchain data, continually refining its knowledge and capabilities. The model is trained to understand the complexities of the blockchain, allowing it to effectively interact with and predict blockchain behaviors. It serves as the foundation for various AI-driven crypto applications, including AI-powered crypto games, DeFi, security solutions, social interactions, asset management, and more.

Key Features of Theia:

Native Understanding of Blockchain: Theia is specifically trained to interpret and simulate the blockchain environment, making it uniquely suited for crypto-native applications.
Advanced Simulation and Reasoning: Capable of understanding, predicting, and interacting with blockchain data in ways that traditional models cannot.
Supports Diverse Applications: From DeFi to security, Theia powers a wide array of AI applications within the crypto space.
Expert-Led Development: Built by a team of AI experts led by a prominent professor in the field, ensuring cutting-edge design and functionality.

What is the Crypto World Model?

The crypto world is built on a massive and rapidly growing body of blockchain data, rich with knowledge and untapped opportunities. Chainbase's approach involves continuously extracting, recording, and organizing this data to make it accessible to downstream users. Despite these efforts, a significant amount of "dark knowledge" within blockchain data remains difficult to access and interpret through traditional databases and manual efforts. Theia addresses this challenge by providing a model that can efficiently understand and utilize this hidden knowledge, offering unprecedented insights and interactions for crypto participants.

Get Started with Theia on Hugging Face

This repository hosts the fine-tuned model of Theia, specifically tailored for blockchain-related question answering and interaction. The model is built on Meta-Llama-3.1-8B-Instruct and enhanced with extensive blockchain knowledge curated by Chainbase.

Model Features:

Domain-Specific Knowledge: Optimized for understanding blockchain data and providing accurate, insightful responses related to crypto topics.
Enhanced Interactivity: Designed to effectively communicate and interact with users on blockchain-related queries.
Scalable and Adaptable: Suitable for a wide range of applications, from developers building crypto AI agents to researchers exploring blockchain data.

How to Use

You can use Theia directly from Hugging Face for various blockchain-related tasks. For detailed instructions on how to integrate and deploy the model, please refer to the Getting Started section in this repository.

Contributing

We welcome contributions from the community to help improve Theia and expand its capabilities. Please feel free to raise issues, submit pull requests, or provide feedback to help us refine the model.

License

Theia is released under the [appropriate license] that governs its use. Please review the license details for more information on how you can use and contribute to the model.

For more information, please visit our official Chainbase website or contact our team at support@chainbase.com.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for zaroaChin/crypto_model

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(637)

this model