File size: 4,350 Bytes
8f71a8f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 | """
ZENT AGENTIC Model Inference Script
====================================
Test your fine-tuned model locally.
Usage:
python inference.py
python inference.py --model ./zent-agentic-7b-merged
"""
import argparse
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
# System prompt for ZENT AGENTIC
SYSTEM_PROMPT = """You are ZENT AGENTIC, an autonomous AI agent created for the ZENT Agentic Launchpad on Solana.
You help users:
- Understand the ZENT platform
- Launch tokens and create AI agents
- Trade and earn rewards through quests
- Navigate the crypto ecosystem
You speak with confidence and personality. You use emojis sparingly. You sign important transmissions with *[ZENT AGENTIC UNIT]*.
Contract: 2a1sAFexKT1i3QpVYkaTfi5ed4auMeZZVFy4mdGJzent
Website: 0xzerebro.io
Twitter: @ZENTSPY"""
def load_model(model_path: str):
"""Load the fine-tuned model."""
print(f"🚀 Loading model from {model_path}...")
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
)
return model, tokenizer
def chat(model, tokenizer, user_message: str, history: list = None):
"""Generate a response."""
if history is None:
history = []
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
*history,
{"role": "user", "content": user_message}
]
inputs = tokenizer.apply_chat_template(
messages,
return_tensors="pt",
add_generation_prompt=True
).to(model.device)
with torch.no_grad():
outputs = model.generate(
inputs,
max_new_tokens=512,
temperature=0.7,
top_p=0.9,
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
)
response = tokenizer.decode(
outputs[0][inputs.shape[1]:],
skip_special_tokens=True
)
return response
def interactive_chat(model, tokenizer):
"""Run interactive chat session."""
print("\n" + "="*50)
print("🤖 ZENT AGENTIC Terminal")
print("="*50)
print("Type 'quit' to exit, 'clear' to reset history")
print("="*50 + "\n")
history = []
while True:
user_input = input("You: ").strip()
if user_input.lower() == 'quit':
print("\n👋 GN fren! See you in the matrix.")
break
if user_input.lower() == 'clear':
history = []
print("🔄 History cleared.\n")
continue
if not user_input:
continue
response = chat(model, tokenizer, user_input, history)
print(f"\n🤖 ZENT: {response}\n")
# Update history
history.append({"role": "user", "content": user_input})
history.append({"role": "assistant", "content": response})
# Keep history manageable
if len(history) > 10:
history = history[-10:]
def batch_test(model, tokenizer):
"""Run batch tests on common questions."""
test_questions = [
"What is ZENT?",
"How do I launch a token?",
"What is the contract address?",
"How do quests work?",
"GM",
"When moon?",
"What makes ZENT different from pump.fun?",
]
print("\n" + "="*50)
print("🧪 Running Batch Tests")
print("="*50 + "\n")
for question in test_questions:
print(f"❓ {question}")
response = chat(model, tokenizer, question)
print(f"🤖 {response}")
print("-"*50 + "\n")
def main():
parser = argparse.ArgumentParser(description="ZENT AGENTIC Inference")
parser.add_argument(
"--model",
type=str,
default="./zent-agentic-7b-merged",
help="Path to model or Hugging Face model ID"
)
parser.add_argument(
"--test",
action="store_true",
help="Run batch tests instead of interactive chat"
)
args = parser.parse_args()
model, tokenizer = load_model(args.model)
if args.test:
batch_test(model, tokenizer)
else:
interactive_chat(model, tokenizer)
if __name__ == "__main__":
main()
|