bounty-hunter

BitAgent Subnet Model

This model is submitted for evaluation in the BitAgent subnet (SN20) on the Bittensor network.

Base Model

This model is based on facebook/opt-125m, which is a small language model that serves as a placeholder. For production use, this would be replaced with a more capable model like Mistral-7B or similar.

Capabilities

• Instruction following
• Tool usage
• Chat completion

Usage

This model can be used with the Transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("den1125/bounty-hunter")
tokenizer = AutoTokenizer.from_pretrained("den1125/bounty-hunter")

# For chat completion
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What can you do?"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)