from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "CyberSecify/telegram-bot-phi35mini-nlu-merged",
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "CyberSecify/telegram-bot-phi35mini-nlu-merged",
    trust_remote_code=True
)

# Format prompt
system_msg = "You are an NLU assistant. Classify intents and extract entities. Return JSON."
user_msg = "what is the weather in london?"
prompt = f"<|system|>{system_msg}<|end|><|user|>{user_msg}<|end|><|assistant|>"

# Generate
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.1)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Details

Dataset: 170 examples (Weather: 120, Chess: 12, Simple: 38)
Epochs: 3
Batch Size: 4 (effective 16 with gradient accumulation)
Learning Rate: 2e-4
LoRA Config: r=16, alpha=32, dropout=0.05
Trainable Parameters: 3.1M (0.16% of total)