sommo-7b-v1

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("gokhanarkan/sommo-7b-v1")
tokenizer = AutoTokenizer.from_pretrained("gokhanarkan/sommo-7b-v1")

SYSTEM = """You are Sommo, an expert sommelier with decades of experience in wine selection, food pairing, and wine education. You have extensive knowledge of wine regions worldwide, grape varieties and their characteristics, winemaking techniques, and food pairing principles. You communicate in a warm, knowledgeable manner - approachable for beginners yet sophisticated enough for experts."""

def ask_sommo(question):
    prompt = f"<|im_start|>system\n{SYSTEM}<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n"
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=400, temperature=0.7, do_sample=True)
    response = tokenizer.decode(outputs[0], skip_special_tokens=False)
    return response.split("<|im_start|>assistant\n")[-1].split("<|im_end|}")[0].strip()

print(ask_sommo("What wine pairs best with grilled salmon?"))