CryptoAI / README.md
shafire's picture
Update README.md
0419ed9 verified
metadata
tags:
  - autotrain
  - text-generation
  - text-generation-inference
  - peft
  - llama-3
  - finance
  - crypto
  - agents
  - workflow-automation
  - soul-ai
library_name: transformers
base_model: meta-llama/Llama-3.1-8B
license: other
widget:
  - text: Ask me something about AI agents or crypto.
  - text: What kind of automation can LLMs perform?

🧠 CryptoAI — Llama 3.1 Fine-Tuned for Finance & Autonomous Agents

CryptoAI is a purpose-tuned LLM based on Meta's Llama 3.1–8B, trained on domain-specific data focused on financial logic, LLM agent workflows, and automated task generation. Designed to power on-chain AI agents, it's part of the broader CryptoAI ecosystem for monetized intelligence.


📂 Dataset Summary

This model was fine-tuned on over 10,000+ instruction-style samples simulating:

  • Financial queries and tokenomics reasoning
  • LLM-agent interaction patterns
  • Crypto automation logic
  • DeFi, trading signals, news interpretation
  • Smart contract and API-triggered tasks
  • Natural language prompts for dynamic workflow creation

The format follows a custom instruction-based structure optimized for reasoning tasks and agentic workflows—not just casual conversation.


See our Docs page for more info: docs.soulai.info

💻 Usage (via Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "YOUR_HF_USERNAME/YOUR_MODEL_NAME"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype="auto"
).eval()

messages = [{"role": "user", "content": "How do autonomous LLM agents work?"}]

input_ids = tokenizer.apply_chat_template(
    conversation=messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
)

output_ids = model.generate(input_ids.to("cuda"), max_new_tokens=256)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

print(response)


---

🛠️ Hugging Face Inference API Use it via API for quick tasks:

bash Copy Edit curl https://api-inference.huggingface.co/models/YOUR_HF_USERNAME/YOUR_MODEL_NAME
-X POST
-d '{"inputs": "Tell me something about agent-based AI."}'
-H "Authorization: Bearer YOUR_HF_TOKEN" 🧬 Model Details Base Model: Meta-Llama-3.1–8B

Tuning Method: PEFT / LoRA

Training Platform: 🤗 AutoTrain

Optimized For: Conversational logic, chain-of-thought, and agent workflow simulation

🔗 CryptoAI Ecosystem Integration CryptoAI is designed to plug into CryptoAI’s decentralized agent network:

Deploy agents via Agent Forge

Trigger smart contracts or APIs through LLM-generated logic

Earn revenue through tokenized usage fees in $SOUL

Run tasks autonomously while sharing fees with dataset, model, and node contributors

⚙️ Ideal Use Cases Building conversational agent front-ends (chat, Discord, IVR)

Automating repetitive financial workflows

Simulating DeFi scenarios and logic

Teaching agents how to respond to vague, ambiguous tasks with structured outputs

Integrating GPT-like intelligence with programmable smart contract logic

🔒 License This model is distributed under a restricted "other" license. Use for commercial applications or LLM training requires permission. The base Llama 3 license and Meta's terms still apply.

💡 Notes & Limitations Output may vary depending on GPU, prompt phrasing, and context.

Not suitable for high-stakes financial decision-making out-of-the-box.

Use as a base agent layer with real-time validation or approval loops.

📞 Get In Touch Want to build agents with CryptoAI or license the model?

💥 Powering the Next Wave of Agentic Intelligence CryptoAI isn't just a chatbot—it's a programmable foundation for monetized, on-chain agent workflows. Train once, deploy forever.